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

    Neuronpedia

    INDEX
    Explanations

    targeting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     twee
    -0.06
     کو
    -0.06
     ذ
    -0.06
    tell
    -0.06
    NoArgsConstructor
    -0.06
    님의
    -0.06
     وأ
    -0.06
    廳
    -0.06
    标题
    -0.06
     کوتاه
    -0.06
    POSITIVE LOGITS
    �合
    0.07
    -hand
    0.06
     PIC
    0.06
    κρα
    0.06
    _PIPE
    0.06
     Toast
    0.06
    Path
    0.06
     Cube
    0.06
    atura
    0.05
     Survivor
    0.05
    Act Density 0.328%

    No Known Activations