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

    Neuronpedia

    INDEX
    Explanations

    time references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /session
    -0.07
     dar
    -0.07
     empath
    -0.07
     Quotes
    -0.07
     midfielder
    -0.06
     deceive
    -0.06
     Forces
    -0.06
    َل
    -0.06
     LA
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    .Storage
    0.07
     كبيرة
    0.07
    SourceType
    0.06
    (reordered
    0.06
    _CANNOT
    0.06
    овані
    0.06
    ่านมา
    0.06
    ‰
    0.06
     finden
    0.06
    bersome
    0.06
    Act Density 0.021%

    No Known Activations