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

    Neuronpedia

    INDEX
    Explanations

    challenge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .skip
    -0.07
     pastors
    -0.06
     июля
    -0.06
    Short
    -0.06
     widow
    -0.06
    <const
    -0.06
     assistants
    -0.06
     června
    -0.06
    ')}}">
    -0.06
    foreign
    -0.06
    POSITIVE LOGITS
    ROT
    0.08
     Incorrect
    0.07
     demanding
    0.06
     inscription
    0.06
    _velocity
    0.06
    .datab
    0.06
    INCLUDED
    0.06
     Facial
    0.06
     hin
    0.06
    arith
    0.06
    Act Density 0.017%

    No Known Activations