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

    Neuronpedia

    INDEX
    Explanations

    Returning/moving backwards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gm
    -0.07
    _TREE
    -0.06
    edly
    -0.06
     Zurich
    -0.06
    Ê
    -0.06
     Ш
    -0.06
    ,long
    -0.06
     bishops
    -0.06
     всегда
    -0.06
     Guild
    -0.06
    POSITIVE LOGITS
    expression
    0.07
    build
    0.06
     لدي
    0.06
    @student
    0.06
    فاق
    0.06
    lius
    0.06
     destructive
    0.06
    aging
    0.06
     Hydra
    0.06
    探
    0.06
    Act Density 0.014%

    No Known Activations