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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кому
    -0.07
    ochen
    -0.07
    Ｂ
    -0.07
    Tac
    -0.07
    sterol
    -0.07
    Grand
    -0.06
    SPACE
    -0.06
    Temp
    -0.06
     spectrum
    -0.06
    phetamine
    -0.06
    POSITIVE LOGITS
    	tests
    0.06
    eguard
    0.06
     Greeks
    0.06
    楼
    0.06
     všichni
    0.06
     (![
    0.06
    ή
    0.06
    aned
    0.06
    ,,,,
    0.06
    ωμά
    0.06
    Act Density 0.118%

    No Known Activations