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

    Neuronpedia

    INDEX
    Explanations

    exponential expansion and multiplication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     administration
    0.56
     kesin
    0.55
     interim
    0.54
     five
    0.54
     departure
    0.54
     te
    0.52
     two
    0.52
     movie
    0.52
     number
    0.51
     session
    0.50
    POSITIVE LOGITS
    lly
    0.56
    setIs
    0.53
    oomla
    0.52
    сову
    0.51
    nés
    0.49
     ໜອງ
    0.49
    Coref
    0.49
    rsa
    0.48
    tze
    0.48
     Meesho
    0.47
    Act Density 0.000%

    No Known Activations