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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اطق
    -0.07
     SIN
    -0.06
    ім
    -0.06
    _Float
    -0.06
     Standards
    -0.06
     Integrity
    -0.06
    Kal
    -0.06
    	q
    -0.06
    Spain
    -0.06
    Patterns
    -0.05
    POSITIVE LOGITS
     guilty
    0.07
     olay
    0.07
    _gui
    0.07
     fuss
    0.07
    _adv
    0.06
     kdo
    0.06
     arşiv
    0.06
    \Security
    0.06
     drugs
    0.06
    Reader
    0.06
    Act Density 0.051%

    No Known Activations