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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iden
    -0.07
     compromise
    -0.07
    CheckBox
    -0.06
    Guess
    -0.06
    -being
    -0.06
     pk
    -0.06
    ेल
    -0.06
    иш
    -0.06
    Center
    -0.06
    night
    -0.06
    POSITIVE LOGITS
     sil
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.07
     уточ
    0.06
     hứ
    0.06
    突
    0.06
     awarded
    0.06
    Dept
    0.06
    开展
    0.06
    };
↵
↵
    0.06
    _slot
    0.06
    Act Density 0.002%

    No Known Activations