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

    Neuronpedia

    INDEX
    Explanations

    Code and calculators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()",
    -0.07
     záznam
    -0.06
    MH
    -0.06
    DetailsService
    -0.06
     geen
    -0.06
    innerHTML
    -0.06
    _gr
    -0.06
    }'
    -0.06
     카
    -0.06
    _management
    -0.06
    POSITIVE LOGITS
     Decision
    0.07
    venue
    0.06
    _construct
    0.06
     pounds
    0.06
    优秀
    0.06
     undergone
    0.06
     Delaware
    0.06
    励
    0.06
     Iceland
    0.06
    .BatchNorm
    0.06
    Act Density 0.013%

    No Known Activations