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

    Neuronpedia

    INDEX
    Explanations

    Special characters/symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endurance
    -0.07
    iado
    -0.07
     назнач
    -0.07
    к
    -0.07
    SCRIPTOR
    -0.06
     अन
    -0.06
    ころ
    -0.06
    ्न
    -0.06
     sayısı
    -0.06
     endiş
    -0.06
    POSITIVE LOGITS
    *t
    0.07
    xyz
    0.07
     الدم
    0.06
    .EMAIL
    0.06
    \Service
    0.06
    ~~
    0.06
     Avoid
    0.06
     풀
    0.06
    _ps
    0.06
     구
    0.06
    Act Density 0.012%

    No Known Activations