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

    Neuronpedia

    INDEX
    Explanations

    code serialization/deserialization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spoiler
    -0.06
     pumped
    -0.06
    OrElse
    -0.06
     Disabled
    -0.06
    olved
    -0.06
    elems
    -0.06
     iw
    -0.06
     quest
    -0.06
     possibility
    -0.06
     threads
    -0.06
    POSITIVE LOGITS
     unix
    0.07
     nej
    0.07
    точ
    0.07
    .Internal
    0.07
    _rep
    0.07
    (browser
    0.07
     Pradesh
    0.07
    {Name
    0.07
    ('/:
    0.06
    roleId
    0.06
    Act Density 0.028%

    No Known Activations