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

    Neuronpedia

    INDEX
    Explanations

    end of sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Refuge
    -0.07
    Esc
    -0.07
    Playback
    -0.06
    .fft
    -0.06
    InSection
    -0.06
     причин
    -0.06
     patriotism
    -0.06
    arf
    -0.06
    _using
    -0.06
    udder
    -0.06
    POSITIVE LOGITS
     dikke
    0.06
     šest
    0.06
    anganese
    0.06
     Cindy
    0.06
     pairs
    0.06
    asha
    0.06
     OU
    0.06
    VS
    0.06
    #endregion
    0.06
    
    0.06
    Act Density 0.001%

    No Known Activations