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

    Neuronpedia

    INDEX
    Explanations

    informed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     toda
    -0.06
    ，当
    -0.06
    -expand
    -0.06
    ESİ
    -0.06
    -commercial
    -0.06
    obre
    -0.06
     Austr
    -0.06
     історії
    -0.06
    ])(
    -0.06
     захисту
    -0.06
    POSITIVE LOGITS
     informed
    0.11
    Research
    0.07
     informs
    0.07
    research
    0.07
    ued
    0.07
     Maurit
    0.06
     nutritious
    0.06
     Flake
    0.06
    -answer
    0.06
    SOURCE
    0.06
    Act Density 0.007%

    No Known Activations