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

    Neuronpedia

    INDEX
    Explanations

    Terrorism/errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شود
    -0.08
     households
    -0.07
    ODEV
    -0.07
    yní
    -0.07
     kotlinx
    -0.06
     IMapper
    -0.06
    <form
    -0.06
     seçim
    -0.06
     format
    -0.06
     Capture
    -0.06
    POSITIVE LOGITS
     Zuckerberg
    0.07
    (Json
    0.07
     Terror
    0.06
    ptr
    0.06
    -p
    0.06
     Penalty
    0.06
    leshooting
    0.06
     liter
    0.06
    天天
    0.06
     ガ
    0.06
    Act Density 0.002%

    No Known Activations