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

    Neuronpedia

    INDEX
    Explanations

    Singles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enorme
    -0.07
    altet
    -0.07
    _names
    -0.07
     thông
    -0.07
    _cleanup
    -0.07
     verification
    -0.06
    Mid
    -0.06
    (entries
    -0.06
     notre
    -0.06
    arks
    -0.06
    POSITIVE LOGITS
     heb
    0.07
    ॉट
    0.06
     GUIDE
    0.06
     Invoice
    0.06
    qx
    0.06
     Intr
    0.06
     scri
    0.06
     artic
    0.06
    Entre
    0.06
    (pub
    0.06
    Act Density 0.002%

    No Known Activations