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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enlight
    -0.06
    -0.06
    !!.
    -0.06
    (no
    -0.06
     frying
    -0.06
     fung
    -0.06
    �
    -0.06
    Mods
    -0.06
    .NoArgsConstructor
    -0.06
     nto
    -0.06
    POSITIVE LOGITS
     رفتار
    0.06
     стос
    0.06
     developing
    0.06
     expanding
    0.06
    &(
    0.06
     exporting
    0.06
    }↵
    0.06
     Applies
    0.06
     PTR
    0.06
     Architects
    0.06
    Act Density 0.003%

    No Known Activations