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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glyph
    -0.06
     expressions
    -0.06
    Conversation
    -0.06
     typings
    -0.06
    имер
    -0.06
    Tek
    -0.06
     psycho
    -0.06
     Mek
    -0.06
     Bers
    -0.06
     Ky
    -0.06
    POSITIVE LOGITS
    ん
    0.07
     veel
    0.06
    _server
    0.06
    DOWN
    0.06
     которые
    0.06
    matches
    0.06
    unch
    0.06
     _↵↵
    0.06
    -next
    0.06
     weight
    0.06
    Act Density 0.001%

    No Known Activations