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

    Neuronpedia

    INDEX
    Explanations

    pm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ॉर
    -0.07
     scp
    -0.07
    unta
    -0.07
    ote
    -0.07
     Santo
    -0.07
    _HOR
    -0.06
     voiture
    -0.06
    "W
    -0.06
     enerj
    -0.06
    ظˆط
    -0.06
    POSITIVE LOGITS
    	category
    0.07
    _standard
    0.06
    ERGE
    0.06
     Keeps
    0.06
    estination
    0.06
    θηκε
    0.06
     кор
    0.06
     عد
    0.06
     QPushButton
    0.06
     Bibli
    0.06
    Act Density 0.005%

    No Known Activations