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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sul
    -0.07
    /Login
    -0.06
     Evangel
    -0.06
    .NORMAL
    -0.06
     samples
    -0.06
    CASCADE
    -0.06
     Bethesda
    -0.06
     substit
    -0.06
     hut
    -0.06
     Thin
    -0.06
    POSITIVE LOGITS
     puede
    0.07
    iren
    0.07
    ParseException
    0.07
     possono
    0.07
    아요
    0.07
    ían
    0.06
     достаточно
    0.06
     hely
    0.06
    ाम
    0.06
     общ
    0.06
    Act Density 0.011%

    No Known Activations