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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mustafa
    -0.07
    خصص
    -0.06
    �i
    -0.06
     kür
    -0.06
     Jed
    -0.06
    although
    -0.06
     reiterated
    -0.06
    -HT
    -0.06
     Lak
    -0.06
    ,U
    -0.06
    POSITIVE LOGITS
    .system
    0.06
    τες
    0.06
     chez
    0.06
    ินการ
    0.06
    	active
    0.06
    POSE
    0.06
    dense
    0.06
    ुद
    0.06
    .website
    0.06
     paints
    0.06
    Act Density 0.001%

    No Known Activations