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

    Neuronpedia

    INDEX
    Explanations

    start of phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    edom
    0.42
     način
    0.38
    comings
    0.37
    Zd
    0.37
     खिला
    0.36
    LAN
    0.36
    Grand
    0.36
     outlay
    0.36
    जागरण
    0.36
    aid
    0.35
    POSITIVE LOGITS
     உத்தர
    0.42
    <0xDF>
    0.41
     bacteri
    0.41
     பின்பு
    0.39
     insuring
    0.39
    紜
    0.39
     Divider
    0.39
    本身的
    0.39
     шар
    0.38
    峹
    0.38
    Act Density 0.000%

    No Known Activations