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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بت
    -0.06
    .selected
    -0.06
     jmé
    -0.06
    middle
    -0.06
     schö
    -0.06
     Ко
    -0.05
    Best
    -0.05
    929
    -0.05
    elon
    -0.05
    picked
    -0.05
    POSITIVE LOGITS
     disclosures
    0.08
    Injector
    0.07
    .nih
    0.07
    하기
    0.07
    PointCloud
    0.07
     volume
    0.07
    ximity
    0.07
     watched
    0.07
     Volume
    0.07
     vacuum
    0.07
    Act Density 0.012%

    No Known Activations