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

    Neuronpedia

    INDEX
    Explanations

    study results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     llama
    -0.07
    apper
    -0.07
     },
    -0.07
     mín
    -0.06
    _pf
    -0.06
     �
    -0.06
     mosquito
    -0.06
     ngOnInit
    -0.06
    065
    -0.06
    _high
    -0.06
    POSITIVE LOGITS
    =subprocess
    0.07
     respecto
    0.07
     Comics
    0.06
    VERTEX
    0.06
    часно
    0.06
     законом
    0.06
     mess
    0.06
     Chủ
    0.06
     recession
    0.06
    .formData
    0.06
    Act Density 0.062%

    No Known Activations