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

    Neuronpedia

    INDEX
    Explanations

    code/commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entropy
    -0.07
     gob
    -0.06
     Incorrect
    -0.06
     Dra
    -0.06
    .strftime
    -0.06
    q
    -0.06
    .p
    -0.06
    -linear
    -0.06
     gourmet
    -0.06
     spoiled
    -0.06
    POSITIVE LOGITS
    	Null
    0.08
    NICALL
    0.07
    .gs
    0.07
     gboolean
    0.06
    MON
    0.06
    )_
    0.06
     پاک
    0.06
    -Mobile
    0.06
     utiliz
    0.06
    avascript
    0.06
    Act Density 0.036%

    No Known Activations