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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ropes
    -0.08
    ILLA
    -0.06
    inside
    -0.06
    terior
    -0.06
    Sk
    -0.06
     consume
    -0.06
    _SLEEP
    -0.06
    ,target
    -0.06
    Face
    -0.06
     painting
    -0.06
    POSITIVE LOGITS
    (gen
    0.07
    implemented
    0.07
    getIndex
    0.07
     notifyDataSetChanged
    0.07
    uyệt
    0.06
     magistrate
    0.06
    oglob
    0.06
    (newState
    0.06
     multer
    0.06
     çık
    0.06
    Act Density 0.002%

    No Known Activations