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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phen
    -0.08
     hương
    -0.07
     integral
    -0.07
    alement
    -0.06
    zeigen
    -0.06
    积极性
    -0.06
    烫
    -0.06
     abundance
    -0.06
    !important
    -0.06
    耄
    -0.06
    POSITIVE LOGITS
     clums
    0.07
    _FOREACH
    0.07
    .Dynamic
    0.07
    isex
    0.07
    ;k
    0.06
    _UUID
    0.06
     Yorkshire
    0.06
    缎
    0.06
     Tcl
    0.06
     Occasionally
    0.06
    Act Density 0.051%

    No Known Activations