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

    Neuronpedia

    INDEX
    Explanations

    processes, states, and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ান
    0.71
    р
    0.64
     imposs
    0.62
    ో
    0.61
     zina
    0.61
     oorlog
    0.61
     shameful
    0.61
     achar
    0.61
    od
    0.60
     cuarto
    0.60
    POSITIVE LOGITS
    <unused433>
    0.63
     decays
    0.63
     اقبال
    0.62
     consultations
    0.62
    状况
    0.62
    缴纳
    0.61
    附近
    0.60
    LET
    0.60
    ക്കോ
    0.59
    ll
    0.59
    Act Density 1.444%

    No Known Activations