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

    Neuronpedia

    INDEX
    Explanations

    that adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rinho
    0.40
     น
    0.37
    rā
    0.37
     ನ
    0.36
    gender
    0.36
     ভর্ত
    0.35
     bk
    0.35
    ับสน
    0.35
     Evaluations
    0.34
     Nob
    0.34
    POSITIVE LOGITS
    $.;
    0.43
     হইলাম
    0.40
     dimes
    0.38
     literal
    0.38
    냐면
    0.38
    मेय
    0.38
     સી
    0.38
    楖
    0.37
     Wally
    0.36
    ጅም
    0.36
    Act Density 0.001%

    No Known Activations