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

    Neuronpedia

    INDEX
    Explanations

    IT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aları
    -0.08
    AINS
    -0.07
    enu
    -0.07
    avoid
    -0.06
    non
    -0.06
     проц
    -0.06
    queen
    -0.06
    rière
    -0.06
    finished
    -0.06
    лер
    -0.06
    POSITIVE LOGITS
    0.07
    []{"
    0.07
    timestamp
    0.07
     \''
    0.06
     dém
    0.06
     SEE
    0.06
    737
    0.06
    /************************************************************************
    0.06
    #####↵
    0.06
    697
    0.06
    Act Density 0.033%

    No Known Activations