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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Odyssey
    -0.07
     niche
    -0.07
    -parameter
    -0.07
    quests
    -0.07
    implemented
    -0.07
     franchises
    -0.06
    色的
    -0.06
    ちは
    -0.06
    (origin
    -0.06
     navCtrl
    -0.06
    POSITIVE LOGITS
     interiors
    0.06
    _PROFILE
    0.06
    _DECLS
    0.06
    지노
    0.06
    ез
    0.06
    sono
    0.06
    NS
    0.06
     VIN
    0.06
    072
    0.06
    WXYZ
    0.05
    Act Density 0.053%

    No Known Activations