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

    Neuronpedia

    INDEX
    Explanations

    ArgumentNullException

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :Any
    -0.07
     LinkedIn
    -0.07
    graduate
    -0.07
    Charts
    -0.07
     Linkedin
    -0.07
    {//
    -0.07
    multiply
    -0.07
    _dx
    -0.07
     сейчас
    -0.07
     Flu
    -0.07
    POSITIVE LOGITS
    ILD
    0.07
     حد
    0.07
    🏳
    0.06
    .bunifu
    0.06
     Seah
    0.06
    ßen
    0.06
    郑重
    0.06
    _UNS
    0.06
    性价
    0.06
    avior
    0.06
    Act Density 0.005%

    No Known Activations