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

    Neuronpedia

    INDEX
    Explanations

    Software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commanding
    -0.07
    แ
    -0.06
    FromDate
    -0.06
     भ
    -0.06
     उल
    -0.06
     bell
    -0.06
     ऐ
    -0.06
    ์บ
    -0.06
     thicker
    -0.06
    ча
    -0.06
    POSITIVE LOGITS
    /std
    0.07
    Something
    0.07
    .";↵
    0.06
    Samples
    0.06
     Andrea
    0.06
    다는
    0.06
     Mut
    0.06
     attn
    0.06
    高等
    0.06
    mut
    0.06
    Act Density 0.001%

    No Known Activations