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

    Neuronpedia

    INDEX
    Explanations

    varied text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [{"
    -0.07
    gis
    -0.07
     compromising
    -0.07
    _project
    -0.07
     إلي
    -0.06
     pj
    -0.06
    jni
    -0.06
     Fra
    -0.06
     presents
    -0.06
     RG
    -0.06
    POSITIVE LOGITS
     miles
    0.07
     premise
    0.07
    ایش
    0.06
     هست
    0.06
    .more
    0.06
    τς
    0.06
     Leer
    0.06
    .op
    0.06
    agen
    0.06
    ")),↵
    0.06
    Act Density 0.000%

    No Known Activations