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

    Neuronpedia

    INDEX
    Explanations

    , followed by digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     margarine
    0.70
     despite
    0.69
     prison
    0.66
     Ansible
    0.65
     आदित्यनाथ
    0.65
     according
    0.65
     everyone
    0.64
     fatta
    0.64
     Aniston
    0.63
     Tregs
    0.63
    POSITIVE LOGITS
    ತ್ಮ
    0.73
     kej
    0.66
    ificateur
    0.66
     fluido
    0.63
    Equivalent
    0.62
    న్
    0.62
    unit
    0.62
    惑
    0.61
    kehr
    0.61
    ൻ
    0.60
    Act Density 0.008%

    No Known Activations