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

    Neuronpedia

    INDEX
    Explanations

    words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     situated
    -0.07
    Reality
    -0.06
    -txt
    -0.06
    .panelControl
    -0.06
    idget
    -0.06
    .guard
    -0.06
     enlargement
    -0.06
     академ
    -0.06
     انسان
    -0.06
    thenReturn
    -0.06
    POSITIVE LOGITS
    ifiers
    0.07
    ;//
    0.07
    IFIER
    0.07
    loon
    0.06
     Tear
    0.06
    -educated
    0.06
    .Pattern
    0.06
    urity
    0.06
     @{
    0.06
    الة
    0.06
    Act Density 0.004%

    No Known Activations