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

    Neuronpedia

    INDEX
    Explanations

    giveaway comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fortune
    -0.08
     Eden
    -0.07
     cameo
    -0.07
     TextView
    -0.07
     elek
    -0.06
     invading
    -0.06
    秃
    -0.06
     balk
    -0.06
     Undefined
    -0.06
     ال
    -0.06
    POSITIVE LOGITS
    reibung
    0.07
    olation
    0.07
    人居
    0.07
     reclaimed
    0.07
     ואף
    0.07
     MEDIA
    0.07
    ública
    0.07
    counter
    0.07
    뤽
    0.07
    Employ
    0.06
    Act Density 0.016%

    No Known Activations