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

    Neuronpedia

    INDEX
    Explanations

    988

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    liceerd
    0.66
    agascar
    0.64
    र्तन
    0.63
     superl
    0.62
    టర్
    0.61
    haz
    0.60
     यूं
    0.60
    rd
    0.59
     সেলিম
    0.59
    ታል
    0.59
    POSITIVE LOGITS
     Rockwell
    0.71
    缥
    0.68
    讲
    0.66
    igli
    0.65
     ви
    0.65
    zigzag
    0.64
    yao
    0.64
    Nex
    0.64
     tooth
    0.63
     tang
    0.63
    Act Density 0.268%

    No Known Activations