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

    Neuronpedia

    INDEX
    Explanations

    units of time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐀
    0.52
     acus
    0.49
     znak
    0.47
     kereta
    0.47
    অর্
    0.46
     wsk
    0.46
     svil
    0.46
     esimerk
    0.46
    ਕ
    0.45
    ोत
    0.45
    POSITIVE LOGITS
    MM
    0.47
    IX
    0.45
    ر
    0.45
    ли
    0.44
    ħ
    0.43
     semidefinite
    0.42
    ளவு
    0.42
     رمضان
    0.42
     formalin
    0.42
    時間
    0.42
    Act Density 0.220%

    No Known Activations