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

    Neuronpedia

    INDEX
    Explanations

    Uncertainty or disbelief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Da
    -0.07
     forwards
    -0.06
     Dublin
    -0.06
     planted
    -0.06
     infant
    -0.06
     Met
    -0.06
     pestic
    -0.06
     Babies
    -0.06
     rookie
    -0.06
     equity
    -0.06
    POSITIVE LOGITS
    elerinin
    0.07
     Worse
    0.07
     belirlen
    0.06
    _atts
    0.06
    maları
    0.06
     lastName
    0.06
    cmath
    0.06
    udos
    0.06
    _Customer
    0.06
    orgh
    0.06
    Act Density 0.033%

    No Known Activations