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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and acronyms, often including parentheses, dashes, and numerical digits

    oai_token-act-pair · gemini-2.0-flash

    acronyms, codes, initialisms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CO
    -0.85
     COT
    -0.83
     CQ
    -0.79
     Co
    -0.79
     c
    -0.77
     resourceCulture
    -0.76
     COE
    -0.75
     Coh
    -0.74
     CDA
    -0.73
     Coss
    -0.71
    POSITIVE LOGITS
    McC
    0.57
    ec
    0.56
     McC
    0.56
    MC
    0.54
    eci
    0.54
     MC
    0.53
    gca
    0.53
    tica
    0.53
    ICA
    0.52
    RC
    0.52
    Act Density 3.098%

    No Known Activations