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

    Neuronpedia

    INDEX
    Explanations

    crush / CSR / stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кто
    0.53
     خ
    0.52
    usi
    0.52
    ارك
    0.52
    다
    0.52
    ون
    0.51
     साक्षी
    0.51
    че
    0.50
    ي
    0.50
    ac
    0.49
    POSITIVE LOGITS
     hamstring
    0.61
     bucket
    0.57
     wavenumber
    0.55
     hashing
    0.54
     dissatisf
    0.54
     lineman
    0.54
     tangerine
    0.54
     dryer
    0.53
     veniam
    0.53
    Bucket
    0.52
    Act Density 0.000%

    No Known Activations