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

    Neuronpedia

    INDEX
    Explanations

    date

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quanto
    -0.08
    ADB
    -0.07
    Sock
    -0.07
    onder
    -0.07
    ông
    -0.07
     Weiter
    -0.06
     socks
    -0.06
     rhythms
    -0.06
     sock
    -0.06
     więcej
    -0.06
    POSITIVE LOGITS
    _lcd
    0.06
     perso
    0.06
    .Text
    0.06
    κει
    0.06
    noise
    0.06
    پ
    0.06
    -Men
    0.06
    addAction
    0.06
    rvine
    0.06
    ி
    0.06
    Act Density 0.002%

    No Known Activations