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

    Neuronpedia

    INDEX
    Explanations

    one-size-fits-all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     percentuale
    0.46
     causada
    0.46
     Lors
    0.42
     arrondies
    0.42
     dihedral
    0.42
    ໃນ
    0.41
    由于
    0.41
     Dolphins
    0.41
     阿
    0.40
     inhalation
    0.40
    POSITIVE LOGITS
    knowledge
    0.48
    solution
    0.46
    v
    0.44
    elfare
    0.44
    arquía
    0.44
    ght
    0.43
     паліты
    0.43
    services
    0.43
     इज
    0.43
    datab
    0.43
    Act Density 0.014%

    No Known Activations