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

    Neuronpedia

    INDEX
    Explanations

    Multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     அவ
    -0.09
     Hay
    -0.09
     പ്രത
    -0.08
     Ice
    -0.08
     Australia's
    -0.08
     Canada's
    -0.08
     вд
    -0.08
     ice
    -0.07
     ಅವ
    -0.07
     అవ
    -0.07
    POSITIVE LOGITS
    _BEGIN
    0.08
     fahr
    0.08
    649
    0.07
    -bearing
    0.07
    crm
    0.07
    _holder
    0.07
     utilisateur
    0.07
    Five
    0.07
    aggia
    0.07
    ಕ್ಕಾಗಿ
    0.07
    Act Density 0.090%

    No Known Activations