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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NO
    -0.07
     말씀
    -0.07
    ullet
    -0.07
     hull
    -0.06
    zv
    -0.06
    Issuer
    -0.06
    Properties
    -0.06
    ustum
    -0.06
     حرف
    -0.06
    .pkl
    -0.06
    POSITIVE LOGITS
     bä
    0.06
     tiếng
    0.06
    compiled
    0.06
     fabricated
    0.06
    embro
    0.06
     과
    0.05
     cáo
    0.05
     counseling
    0.05
    gay
    0.05
     Ms
    0.05
    Act Density 0.026%

    No Known Activations