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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ombre
    -0.07
    erusform
    -0.06
    addError
    -0.06
     wondered
    -0.06
    avings
    -0.06
    615
    -0.06
     ""
    -0.06
    曾
    -0.06
    ОВ
    -0.06
    $result
    -0.06
    POSITIVE LOGITS
     at
    0.08
     Pv
    0.07
     �
    0.07
     mys
    0.06
     अग
    0.06
     вог
    0.06
     کنید
    0.06
    约
    0.06
    jsc
    0.06
    Illuminate
    0.06
    Act Density 0.027%

    No Known Activations