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

    Neuronpedia

    INDEX
    Explanations

    ck

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fan
    -0.08
     Phú
    -0.07
    onical
    -0.07
    фра
    -0.07
    ائية
    -0.07
    ्रध
    -0.07
    _tw
    -0.07
    Wel
    -0.07
    eph
    -0.07
    �
    -0.06
    POSITIVE LOGITS
     neck
    0.16
     Neck
    0.13
    -neck
    0.10
    neck
    0.10
    izers
    0.07
     necklace
    0.07
     nonce
    0.07
     nek
    0.07
     scalp
    0.07
    head
    0.06
    Act Density 0.005%

    No Known Activations