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

    Neuronpedia

    INDEX
    Explanations

    json Column or row 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ٫
    0.43
    nonumber
    0.38
     aforesaid
    0.37
     aforementioned
    0.36
    áin
    0.35
     سواء
    0.35
    ørn
    0.34
     सौंपी
    0.34
    ดังกล่าว
    0.33
     Rajapak
    0.33
    POSITIVE LOGITS
     hanger
    0.37
     cooper
    0.35
    嚎
    0.35
    Resol
    0.34
    ‌است
    0.34
     pilot
    0.33
     Resol
    0.33
     naughty
    0.33
     homelessness
    0.33
     hangar
    0.32
    Act Density 0.255%

    No Known Activations