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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PILE
    -0.06
     starting
    -0.06
    Superview
    -0.06
    Fa
    -0.06
    encing
    -0.06
     učitel
    -0.06
    )L
    -0.06
    Modifiers
    -0.06
     Understanding
    -0.06
     Finger
    -0.06
    POSITIVE LOGITS
    _losses
    0.07
    'était
    0.07
    Iran
    0.06
    tplib
    0.06
    าล
    0.06
    .userId
    0.06
     사람
    0.06
    _final
    0.06
    (web
    0.06
    _fft
    0.06
    Act Density 0.053%

    No Known Activations