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
    	signal
    -0.07
    (Stream
    -0.07
     vál
    -0.07
     ensuite
    -0.07
     alanda
    -0.07
     era
    -0.07
     FN
    -0.06
     busty
    -0.06
     },↵
    -0.06
     webinar
    -0.06
    POSITIVE LOGITS
    pedo
    0.06
     иг
    0.06
     nuis
    0.06
    事務
    0.06
     MET
    0.06
    amina
    0.05
    horizontal
    0.05
    ichi
    0.05
    Beta
    0.05
    integer
    0.05
    Act Density 0.005%

    No Known Activations