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

    Neuronpedia

    INDEX
    Explanations

    placed under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    āt
    0.77
     aufs
    0.75
    ঞ্জের
    0.73
     activate
    0.73
    ansh
    0.73
     സംവിധ
    0.73
    पोर्ट
    0.71
    組立
    0.70
     myśl
    0.69
     நல
    0.69
    POSITIVE LOGITS
     अपराधी
    0.63
    タミン
    0.63
    wed
    0.62
    বণ
    0.61
     expositions
    0.60
     evaporator
    0.59
    ວກ
    0.58
    ешь
    0.58
     अपॉ
    0.58
    ἱ
    0.58
    Act Density 0.000%

    No Known Activations