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

    Neuronpedia

    INDEX
    Explanations

    select

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iped
    -0.07
    ６
    -0.07
    panels
    -0.06
    _idxs
    -0.06
    xae
    -0.06
     cock
    -0.06
     Simpsons
    -0.06
    claims
    -0.06
     कभ
    -0.06
    рощ
    -0.06
    POSITIVE LOGITS
    ές
    0.07
    /effects
    0.06
     stool
    0.06
     Matthew
    0.06
    malloc
    0.06
     proposal
    0.06
     personality
    0.06
     assh
    0.06
    .prevent
    0.05
     ответствен
    0.05
    Act Density 0.002%

    No Known Activations