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

    Neuronpedia

    INDEX
    Explanations

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '_',
    -0.07
    かけ
    -0.07
     rock
    -0.07
    킬
    -0.06
    Week
    -0.06
     obou
    -0.06
     artists
    -0.06
     nose
    -0.06
    ifes
    -0.06
     стор
    -0.06
    POSITIVE LOGITS
    Email
    0.06
     спеці
    0.06
     bouts
    0.06
    _PM
    0.06
     condoms
    0.06
     مهم
    0.06
     mockMvc
    0.06
     csak
    0.06
     школи
    0.06
    _SZ
    0.06
    Act Density 0.008%

    No Known Activations