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

    Neuronpedia

    INDEX
    Explanations

    R

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anding
    -0.08
     Cùng
    -0.08
    Pg
    -0.07
     cursos
    -0.07
    險
    -0.07
     towels
    -0.07
     หาก
    -0.07
    ��
    -0.07
    HX
    -0.07
    ක
    -0.07
    POSITIVE LOGITS
    新冠
    0.07
    无所谓
    0.07
    .JSONException
    0.07
     Alamofire
    0.07
    влекатель
    0.07
     Frag
    0.07
    NR
    0.07
    爪
    0.06
     weekends
    0.06
     viewpoint
    0.06
    Act Density 0.014%

    No Known Activations