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

    Neuronpedia

    INDEX
    Explanations

    Lists or definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :pointer
    -0.07
    ional
    -0.07
    player
    -0.07
     resend
    -0.07
    _confirm
    -0.06
    after
    -0.06
    ')}}"
    -0.06
    whether
    -0.06
    $client
    -0.06
     molding
    -0.06
    POSITIVE LOGITS
     справж
    0.07
    座
    0.06
     '',
    0.06
     Were
    0.06
     geographic
    0.06
     series
    0.06
     ',
    0.06
     село
    0.06
     Short
    0.06
     tenant
    0.06
    Act Density 0.062%

    No Known Activations