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

    Neuronpedia

    INDEX
    Explanations

    framework

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ивания
    -0.08
     đa
    -0.07
    imals
    -0.06
     multiplication
    -0.06
     relocation
    -0.06
     Telefon
    -0.06
     sạch
    -0.06
     이벤트
    -0.06
     tedbir
    -0.06
    itation
    -0.06
    POSITIVE LOGITS
     French
    0.08
    arsers
    0.07
     Frank
    0.07
     endforeach
    0.07
     رفتار
    0.07
    _minimum
    0.07
     pioneered
    0.06
    vv
    0.06
     desenv
    0.06
     claim
    0.06
    Act Density 0.011%

    No Known Activations