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

    Neuronpedia

    INDEX
    Explanations

    defining a term

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rai
    -0.07
    Seconds
    -0.07
    �
    -0.07
    .Does
    -0.06
     PLAN
    -0.06
    �
    -0.06
     beds
    -0.06
    .nlm
    -0.06
     рекомен
    -0.06
     capsules
    -0.06
    POSITIVE LOGITS
     정신
    0.07
     증가
    0.06
    *m
    0.06
     proletariat
    0.06
     callee
    0.06
    	fp
    0.06
     alist
    0.06
    etermination
    0.06
     knows
    0.06
     henüz
    0.06
    Act Density 0.032%

    No Known Activations