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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     machines
    -0.07
    udiant
    -0.07
    jour
    -0.06
     camping
    -0.06
    _tile
    -0.06
     surgeons
    -0.06
     hopping
    -0.06
     FormBuilder
    -0.06
     makeup
    -0.06
    ROLL
    -0.06
    POSITIVE LOGITS
    解决
    0.07
     bardzo
    0.07
     tehlik
    0.06
     несколько
    0.06
    ême
    0.06
    _keywords
    0.06
     проблем
    0.06
     Assumes
    0.06
     पहल
    0.06
     پیوند
    0.06
    Act Density 0.052%

    No Known Activations