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

    Neuronpedia

    INDEX
    Explanations

    math/scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Iteration
    -0.07
    regions
    -0.07
    chk
    -0.06
    064
    -0.06
    Sheet
    -0.06
     války
    -0.06
    ポ
    -0.06
     rotor
    -0.06
     tard
    -0.06
     dass
    -0.06
    POSITIVE LOGITS
    _PE
    0.06
    	If
    0.06
     معرف
    0.06
    _WHITE
    0.06
    olicies
    0.06
    .spaceBetween
    0.06
     sé
    0.06
     squarely
    0.06
    _MethodInfo
    0.06
    <AM
    0.06
    Act Density 0.046%

    No Known Activations