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

    Neuronpedia

    INDEX
    Explanations

    to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kkal
    0.60
    érica
    0.60
    ْم
    0.60
    ꯤ
    0.59
    ባድ
    0.59
     فونبٹ
    0.59
     Evidently
    0.58
    сная
    0.58
     culminating
    0.58
    ↠
    0.57
    POSITIVE LOGITS
    i
    0.59
    h
    0.56
    al
    0.53
    y
    0.53
    ある
    0.52
    iin
    0.50
    ي
    0.49
    ur
    0.49
    их
    0.48
    tuple
    0.47
    Act Density 0.048%

    No Known Activations