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

    Neuronpedia

    INDEX
    Explanations

    Excerpts from longer texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lore
    -0.07
     geben
    -0.07
     airspace
    -0.07
    icos
    -0.06
     opak
    -0.06
    prs
    -0.06
    _SPLIT
    -0.06
     Brennan
    -0.06
    kraine
    -0.06
     philosopher
    -0.06
    POSITIVE LOGITS
    craper
    0.07
    보
    0.07
     invitations
    0.07
    稍
    0.06
     dlouh
    0.06
     lightweight
    0.06
    维
    0.06
     amateurs
    0.06
     AL
    0.06
     long
    0.06
    Act Density 0.000%

    No Known Activations