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

    Neuronpedia

    INDEX
    Explanations

    XML-based data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clifford
    -0.07
    write
    -0.06
     WRITE
    -0.06
    Vertex
    -0.06
    vincia
    -0.06
     bam
    -0.06
    	↵	↵	↵	↵
    -0.06
    Suffix
    -0.06
     smiling
    -0.06
    Attachments
    -0.06
    POSITIVE LOGITS
    lé
    0.06
    orer
    0.06
     gelen
    0.06
    ाजप
    0.06
    �
    0.06
    -with
    0.06
     villa
    0.06
     inhib
    0.06
     عقد
    0.06
     neuken
    0.06
    Act Density 0.009%

    No Known Activations