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

    Neuronpedia

    INDEX
    Explanations

    comparison operators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ointed
    -0.07
    ERING
    -0.07
    应该
    -0.06
     alte
    -0.06
    літ
    -0.06
    Envelope
    -0.06
    Њ
    -0.06
     kisses
    -0.06
     unsur
    -0.06
     buys
    -0.06
    POSITIVE LOGITS
     cardiac
    0.07
     tolerant
    0.07
     ajud
    0.07
     accompl
    0.06
     isFirst
    0.06
    /head
    0.06
     :,
    0.06
    _ABI
    0.06
    caffe
    0.06
    ฆ
    0.05
    Act Density 0.014%

    No Known Activations