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

    Neuronpedia

    INDEX
    Explanations

    numerical values and references to figures

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

    Hexadecimal byte code

    np_acts-logits-general · gemini-2.0-flash

    stage and figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.64
    SourceChecksum
    -0.51
    SharedCtor
    -0.50
     Cio
    -0.50
     Signalez
    -0.48
    ruk
    -0.48
    aksi
    -0.46
    BL
    -0.46
    BFF
    -0.44
     snippetHide
    -0.44
    POSITIVE LOGITS
     understood
    0.72
     understand
    0.70
     förstå
    0.66
     Understand
    0.65
     Iberia
    0.65
    understand
    0.64
    Understand
    0.62
    zeba
    0.61
     understands
    0.61
     understanding
    0.61
    Act Density 0.715%

    No Known Activations