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

    Neuronpedia

    INDEX
    Explanations

    Actions/Verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .firstname
    -0.07
    ğinden
    -0.06
    subscriptions
    -0.06
     _{}
    -0.06
    togroup
    -0.06
    せ
    -0.06
    .zoom
    -0.06
     Tinder
    -0.06
    ragments
    -0.06
     zoning
    -0.05
    POSITIVE LOGITS
    _PD
    0.07
     HEL
    0.06
    rapper
    0.06
     ELECT
    0.06
    Ac
    0.06
     PASS
    0.06
    GRADE
    0.06
    ♀♀♀♀
    0.06
     undermine
    0.06
     MASTER
    0.06
    Act Density 0.077%

    No Known Activations