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

    Neuronpedia

    INDEX
    Explanations

    How

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pv
    -0.06
    oro
    -0.06
    」↵↵
    -0.06
    ']]↵
    -0.06
     ↵↵
    -0.06
    Representation
    -0.06
    '''↵↵
    -0.06
    lej
    -0.06
    atoi
    -0.06
    _()↵
    -0.06
    POSITIVE LOGITS
    VAS
    0.07
    avirus
    0.07
     poorer
    0.07
    倫
    0.06
     nuclear
    0.06
     Danish
    0.06
     organizations
    0.06
     Tek
    0.06
    mun
    0.06
     douche
    0.06
    Act Density 0.035%

    No Known Activations