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

    Neuronpedia

    INDEX
    Explanations

    Intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grids
    -0.07
    ournament
    -0.07
    zilla
    -0.07
    ichtig
    -0.06
    chestra
    -0.06
    плод
    -0.06
    MBOL
    -0.06
    @$
    -0.06
    克思
    -0.06
    جب
    -0.06
    POSITIVE LOGITS
     propia
    0.07
    🗺
    0.07
    שעה
    0.06
    �
    0.06
    put
    0.06
     الش
    0.06
     내가
    0.06
    الياب
    0.06
    を求め
    0.06
    交流
    0.06
    Act Density 0.027%

    No Known Activations