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

    Neuronpedia

    INDEX
    Explanations

    usability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िकोण
    0.43
    শিকান্ত
    0.37
    SR
    0.36
    ッチン
    0.35
    啱
    0.35
    IVED
    0.35
    elj
    0.35
    ಎಂ
    0.35
    BLIC
    0.35
    ITICAL
    0.35
    POSITIVE LOGITS
     Us
    0.71
    Us
    0.67
     usability
    0.63
    usable
    0.44
     usable
    0.44
     usur
    0.44
     us
    0.42
    Pi
    0.42
    ability
    0.40
    sab
    0.40
    Act Density 0.003%

    No Known Activations