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

    Neuronpedia

    INDEX
    Explanations

    language model prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <number
    -0.09
     Betrieb
    -0.09
     IPC
    -0.08
     מנה
    -0.08
    开奖
    -0.08
     capaciteit
    -0.08
     коммун
    -0.08
     prag
    -0.08
    UIAlert
    -0.08
     مدير
    -0.08
    POSITIVE LOGITS
     torso
    0.16
     શરી
    0.15
     शरीर
    0.14
     anatomical
    0.14
    身体
    0.14
     muscul
    0.13
     anatom
    0.13
     anatomy
    0.13
     abdomen
    0.13
     몸
    0.12
    Act Density 0.125%

    No Known Activations