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

    Neuronpedia

    INDEX
    Explanations

    early

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (images
    -0.06
    ountry
    -0.06
    -ng
    -0.06
    .plist
    -0.06
     рублей
    -0.06
    _RET
    -0.06
     tématu
    -0.06
    isman
    -0.06
     Seven
    -0.06
    .CODE
    -0.06
    POSITIVE LOGITS
     infect
    0.07
     overl
    0.06
     restore
    0.06
    Yahoo
    0.06
    での
    0.06
    okie
    0.06
     early
    0.06
     Dining
    0.06
     توضی
    0.06
     permission
    0.06
    Act Density 0.012%

    No Known Activations