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

    Neuronpedia

    INDEX
    Explanations

    um

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .widget
    -0.07
     idiot
    -0.06
    他の
    -0.06
    ambio
    -0.06
    getActiveSheet
    -0.06
    -To
    -0.06
    _pitch
    -0.06
    -0.06
    üfus
    -0.06
    �
    -0.05
    POSITIVE LOGITS
    (tags
    0.07
    éra
    0.07
     Citizenship
    0.07
     universally
    0.06
     conformity
    0.06
    csr
    0.06
    ACHI
    0.06
    (filter
    0.06
     acompañ
    0.06
     Ernst
    0.06
    Act Density 0.019%

    No Known Activations