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

    Neuronpedia

    INDEX
    Explanations

    absolute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    407
    -0.08
     aktar
    -0.07
     léč
    -0.07
     Mil
    -0.07
     Gür
    -0.06
     courteous
    -0.06
    _packets
    -0.06
    oper
    -0.06
    volent
    -0.06
    .getPosition
    -0.06
    POSITIVE LOGITS
     absolute
    0.08
     Absolute
    0.07
     сут
    0.07
    abe
    0.07
     empower
    0.07
     Mist
    0.07
    WRITE
    0.07
     собствен
    0.06
    ві
    0.06
    _Link
    0.06
    Act Density 0.004%

    No Known Activations