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

    Neuronpedia

    INDEX
    Explanations

    encouraging user action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _prop
    -0.07
    ке
    -0.06
     {}));↵
    -0.06
    _op
    -0.06
    (**
    -0.06
    られている
    -0.06
    ponible
    -0.06
    -Clause
    -0.06
    .');↵↵
    -0.05
    انو
    -0.05
    POSITIVE LOGITS
     banka
    0.08
     INT
    0.08
     نظام
    0.07
    ]:
    0.07
     ds
    0.07
    .netbeans
    0.07
     Bliss
    0.07
     spear
    0.06
     metaphor
    0.06
     své
    0.06
    Act Density 0.003%

    No Known Activations