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

    Neuronpedia

    INDEX
    Explanations

    "@

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stateProvider
    -0.41
     listening
    -0.39
    ence
    -0.39
    fbox
    -0.38
    AccessorTable
    -0.38
    pend
    -0.38
    bians
    -0.37
    chdir
    -0.37
    alu
    -0.37
    enda
    -0.35
    POSITIVE LOGITS
     promulgated
    0.82
    RenderAtEndOf
    0.81
     practised
    0.78
     GenerationType
    0.77
     recited
    0.75
     uſed
    0.74
     uttered
    0.74
     attested
    0.74
     sung
    0.73
    ⓧ
    0.73
    Act Density 0.000%

    No Known Activations