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

    Neuronpedia

    INDEX
    Explanations

    IEP Development and implementation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fuori
    1.94
     endExpNow
    1.68
     encuesta
    1.59
     suur
    1.56
    로
    1.55
    ਰੀ
    1.54
    geq
    1.51
    ப
    1.50
    な
    1.49
     sucesso
    1.49
    POSITIVE LOGITS
     rebell
    1.85
     sedan
    1.79
     Sedan
    1.72
     annihil
    1.55
     уго
    1.55
    1.55
    1.54
    ال
    1.53
    ären
    1.51
     lorem
    1.49
    Act Density 0.000%

    No Known Activations