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

    Neuronpedia

    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ependency
    -0.06
    -Ф
    -0.06
     LS
    -0.06
     Inbox
    -0.06
    Normally
    -0.06
     wooden
    -0.06
     Ae
    -0.06
     topped
    -0.06
     downhill
    -0.06
    ũ
    -0.06
    POSITIVE LOGITS
    Usuario
    0.07
    Type
    0.07
    .modified
    0.07
     tartış
    0.06
    คล
    0.06
    utherford
    0.06
     cryptocurrencies
    0.06
    _variable
    0.06
    (flags
    0.06
     Summary
    0.06
    Act Density 0.000%

    No Known Activations