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

    Neuronpedia

    INDEX
    Explanations

    reporting a problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ammunition
    -0.07
    нів
    -0.06
    láv
    -0.06
    ornment
    -0.06
     Pawn
    -0.06
    òi
    -0.06
    _race
    -0.06
     compil
    -0.06
     �
    -0.06
     scratch
    -0.06
    POSITIVE LOGITS
    _least
    0.07
    ,private
    0.06
     gunshot
    0.06
    .s
    0.06
     의미
    0.06
    :&
    0.06
    -gr
    0.06
     Stability
    0.06
     Τ
    0.06
    (Long
    0.06
    Act Density 0.001%

    No Known Activations