Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to machine learning and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Machine Learning" or related terms

    np_acts-logits-general · gemini-2.0-flash

    Machine Learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.88
    fjspx
    -0.87
     pleaſure
    -0.85
    WebVitals
    -0.83
    Datuak
    -0.83
     hâte
    -0.83
    Portail
    -0.82
     bershka
    -0.82
     EnglishChoose
    -0.81
    InputBorder
    -0.80
    POSITIVE LOGITS
     machines
    1.19
    Machines
    1.16
     Machines
    1.09
     Machine
    1.07
     machine
    1.06
    machines
    1.04
    Machine
    0.97
    machine
    0.95
     MACHINE
    0.91
     MACH
    0.90
    Act Density 0.125%

    No Known Activations