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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     demolished
    -0.06
     hook
    -0.06
     presentation
    -0.06
     creatively
    -0.06
     quiet
    -0.06
    _given
    -0.06
    .Fat
    -0.06
     progress
    -0.06
    loor
    -0.06
     Hancock
    -0.06
    POSITIVE LOGITS
    誉
    0.07
    apr
    0.06
    slu
    0.06
    Gesture
    0.06
     погод
    0.06
     Explicit
    0.06
    นท
    0.06
    arbeit
    0.06
    abama
    0.06
    駐
    0.06
    Act Density 0.041%

    No Known Activations