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

    Neuronpedia

    INDEX
    Explanations

    Noncovalent Interactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ＝
    -0.07
    )value
    -0.07
     invitation
    -0.07
    째
    -0.07
    _msg
    -0.07
    ｂ
    -0.07
     emerge
    -0.06
     couleur
    -0.06
    箫
    -0.06
    (note
    -0.06
    POSITIVE LOGITS
    Reviewer
    0.07
    setattr
    0.07
     prostitut
    0.07
    admins
    0.07
     Tire
    0.06
     Scre
    0.06
    HasColumnType
    0.06
    .Features
    0.06
     autonom
    0.06
     incred
    0.06
    Act Density 0.013%

    No Known Activations