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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ures
    -0.07
     analysts
    -0.07
    bert
    -0.07
    oin
    -0.07
    urer
    -0.06
    raya
    -0.06
    (screen
    -0.06
    Reducers
    -0.06
    -play
    -0.06
    -fe
    -0.06
    POSITIVE LOGITS
    非常
    0.07
     第二
    0.07
    운데
    0.07
     nonexistent
    0.07
    ــــ
    0.06
     얼마
    0.06
    akeFromNib
    0.06
    ',...↵
    0.06
    vably
    0.06
    .Pointer
    0.06
    Act Density 0.439%

    No Known Activations