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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (x
    -0.07
    -eight
    -0.06
    _integration
    -0.06
    executor
    -0.06
    ENG
    -0.06
     hardened
    -0.06
    取
    -0.06
    aces
    -0.06
    Engineering
    -0.06
     evening
    -0.06
    POSITIVE LOGITS
     Puppy
    0.07
    priv
    0.06
     poking
    0.06
     sudah
    0.06
     tornado
    0.06
    vic
    0.06
    .Raycast
    0.06
    坐在
    0.06
     highest
    0.06
     Tooth
    0.06
    Act Density 0.029%

    No Known Activations