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

    Neuronpedia

    INDEX
    Explanations

    research funding, testing, stock photography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yelled
    0.44
     debate
    0.41
    jeni
    0.41
     dje
    0.41
     screamed
    0.40
    ட்டிக்
    0.40
     Chronicle
    0.40
     joked
    0.40
    ories
    0.39
    মানিক
    0.39
    POSITIVE LOGITS
    RELL
    0.35
    وش
    0.35
    ینو
    0.35
    탄
    0.34
    رس
    0.34
    ರ್ಮ
    0.33
     Majorana
    0.33
    혁
    0.33
    ندو
    0.32
    در
    0.32
    Act Density 0.001%

    No Known Activations