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

    Neuronpedia

    INDEX
    Explanations

    parentheses, Dal, Due to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Stick
    0.41
    कन्या
    0.39
    ຯ
    0.39
    리스
    0.39
    缦
    0.38
     stick
    0.38
    Check
    0.38
     ग्रीन
    0.37
    DeleteItem
    0.37
     Check
    0.36
    POSITIVE LOGITS
    umbres
    0.47
    ډ
    0.45
    um
    0.42
    identified
    0.42
     innings
    0.41
    ujemy
    0.41
     extraño
    0.41
    inguishing
    0.40
    un
    0.40
    undred
    0.40
    Act Density 0.001%

    No Known Activations