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

    Neuronpedia

    INDEX
    Explanations

    random characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (!)
    0.32
     advocate
    0.32
     Examining
    0.31
    (!)
    0.29
     Toolkit
    0.28
     Reflections
    0.27
     Fuchs
    0.27
     Putting
    0.27
    fti
    0.27
     advocacy
    0.26
    POSITIVE LOGITS
     पासवर्ड
    0.34
    (''
    0.33
     हमरे
    0.33
    之类的
    0.33
     রক্তের
    0.32
    ο
    0.32
     अंडर
    0.32
    পিন
    0.32
    idoarjo
    0.32
    yeah
    0.31
    Act Density 0.034%

    No Known Activations