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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rewarding
    -0.07
     sanki
    -0.07
     olup
    -0.06
    رود
    -0.06
    乡
    -0.06
    Ty
    -0.06
    luk
    -0.06
     newcomers
    -0.06
     nb
    -0.06
     CLASS
    -0.06
    POSITIVE LOGITS
     Methods
    0.07
     represented
    0.07
     querying
    0.07
     Observable
    0.07
     prognosis
    0.06
     Photon
    0.06
    -growing
    0.06
    unnable
    0.06
     elimin
    0.06
     agile
    0.06
    Act Density 0.000%

    No Known Activations