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

    Neuronpedia

    INDEX
    Explanations

    Separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rail
    -0.07
     all
    -0.07
    स
    -0.06
    _ACTIVITY
    -0.06
    아서
    -0.06
    될
    -0.06
    .drag
    -0.06
     Zack
    -0.06
     Priest
    -0.06
     đốc
    -0.06
    POSITIVE LOGITS
     πάνω
    0.06
    ベル
    0.06
    (Status
    0.06
     annon
    0.06
    	RTCK
    0.06
     عملیات
    0.06
    (range
    0.06
     assumptions
    0.06
    (point
    0.06
    _percentage
    0.05
    Act Density 0.018%

    No Known Activations