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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Warn
    -0.07
     справи
    -0.06
    <S
    -0.06
     why
    -0.06
    _ll
    -0.06
     hakkı
    -0.06
     Wars
    -0.06
    _WRONG
    -0.06
     Why
    -0.06
    (Screen
    -0.06
    POSITIVE LOGITS
     про
    0.07
    �
    0.06
     ож
    0.06
    ，但是
    0.06
    @
    0.06
    调整
    0.06
    첨부
    0.06
    .AnchorStyles
    0.06
     MyClass
    0.06
     kingdoms
    0.06
    Act Density 0.008%

    No Known Activations