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
     Gladiator
    -0.07
     треть
    -0.07
    .dialog
    -0.06
     finer
    -0.06
     Simulation
    -0.06
    _CONNECTED
    -0.06
     감독
    -0.06
    Runnable
    -0.06
    стре
    -0.06
    (dic
    -0.06
    POSITIVE LOGITS
    .fname
    0.07
     Christine
    0.06
     Σ
    0.06
     Deutschland
    0.06
     detach
    0.06
    ænd
    0.06
     keys
    0.06
     horrifying
    0.06
    =json
    0.06
     anarchists
    0.06
    Act Density 0.385%

    No Known Activations