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

    Neuronpedia

    INDEX
    Explanations

    structured data tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    When
    -0.95
    To
    -0.94
    ที่มี
    -0.93
     olvidar
    -0.91
     beliebt
    -0.91
     проблеми
    -0.91
    大家的
    -0.90
     bọn
    -0.90
     codzien
    -0.90
    If
    -0.90
    POSITIVE LOGITS
    menistan
    1.14
    netje
    1.13
    plication
    1.07
    zation
    1.06
     mitte
    1.05
    icoot
    1.03
     tient
    1.03
    naire
    1.02
    izare
    1.00
     Yojana
    0.99
    Act Density 0.005%

    No Known Activations