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

    Neuronpedia

    INDEX
    Explanations

    several States

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ggio
    0.38
     kalam
    0.36
     bể
    0.36
    逸
    0.35
    Kurt
    0.35
    iku
    0.34
     fréquente
    0.34
    িতি
    0.34
     grandson
    0.34
     kh
    0.33
    POSITIVE LOGITS
    bodies
    0.41
    janja
    0.38
    pyrazol
    0.38
    হত্যা
    0.38
     людям
    0.37
     বক্তব
    0.37
    FromFile
    0.37
    வாள
    0.37
    CLASS
    0.36
    odies
    0.36
    Act Density 0.002%

    No Known Activations