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

    Neuronpedia

    INDEX
    Explanations

    ideals, classes, vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ΑΣ
    1.24
     unequivocal
    1.14
     enacted
    1.12
     föld
    1.12
     IFC
    1.11
     Colts
    1.11
    ittarius
    1.11
    entukan
    1.09
     IFSC
    1.09
    ැබ
    1.06
    POSITIVE LOGITS
    Für
    1.11
    가를
    1.01
    {}
    1.00
    每一個
    0.97
     médic
    0.95
    weise
    0.95
     ihres
    0.93
    ဳ
    0.92
    п
    0.91
     próprios
    0.91
    Act Density 0.006%

    No Known Activations