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

    Neuronpedia

    INDEX
    Explanations

    ution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clintons
    -0.07
     Автор
    -0.07
    狙击
    -0.07
     Điện
    -0.07
    ="?
    -0.07
    illard
    -0.07
    계
    -0.07
    ificador
    -0.06
    蹒
    -0.06
    贸
    -0.06
    POSITIVE LOGITS
    人格
    0.08
    .enc
    0.07
    tool
    0.07
    атегор
    0.07
     shortened
    0.07
    parameter
    0.06
     efforts
    0.06
    JECT
    0.06
    uki
    0.06
    ꧈
    0.06
    Act Density 0.007%

    No Known Activations