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

    Neuronpedia

    INDEX
    Explanations

    1 or 0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fabs
    -0.07
    トラブル
    -0.07
    嚆
    -0.07
    질
    -0.07
    𝗶
    -0.07
    🖒
    -0.07
    �
    -0.06
    нтер
    -0.06
     khoản
    -0.06
    🤧
    -0.06
    POSITIVE LOGITS
     suspend
    0.08
     لكن
    0.08
     expansive
    0.07
    城堡
    0.07
    防守
    0.07
     pequeña
    0.07
     pushed
    0.07
    ica
    0.07
     sl
    0.07
    车身
    0.07
    Act Density 0.003%

    No Known Activations