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

    Neuronpedia

    INDEX
    Explanations

    SAMHSA National Helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     view
    0.64
    ter
    0.63
     bay
    0.62
    模特
    0.60
    TER
    0.60
    Ter
    0.60
     Ter
    0.60
     disguised
    0.60
     model
    0.57
     발견
    0.57
    POSITIVE LOGITS
     Совета
    0.69
    <unused68>
    0.65
    ខ្ញ
    0.62
     हा
    0.62
    mese
    0.62
    PlayerDataCache
    0.62
    ក្ត
    0.61
     に対
    0.61
    手を
    0.59
     spokoj
    0.59
    Act Density 0.097%

    No Known Activations