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

    Neuronpedia

    INDEX
    Explanations

    g

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ห
    -0.07
    원의
    -0.06
    itious
    -0.06
    specified
    -0.06
     medic
    -0.06
    FileNotFoundException
    -0.06
    expects
    -0.06
     Télé
    -0.06
    Matching
    -0.06
     Πρό
    -0.06
    POSITIVE LOGITS
    /popper
    0.07
     Or
    0.07
     religious
    0.07
    ,temp
    0.06
    yg
    0.06
    _FORMAT
    0.06
     Daily
    0.06
     öyle
    0.06
     demonic
    0.06
    (Dictionary
    0.06
    Act Density 0.001%

    No Known Activations