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

    Neuronpedia

    INDEX
    Explanations

    support and encouragement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     décrit
    0.39
    ensation
    0.38
     indices
    0.38
    icylic
    0.36
    jResponse
    0.36
     computes
    0.36
    を取得
    0.35
     interacting
    0.35
     วิ
    0.35
     phylogenetic
    0.35
    POSITIVE LOGITS
     support
    1.70
     apoyo
    1.64
    support
    1.56
     supporto
    1.56
    Support
    1.54
     поддержки
    1.48
     Support
    1.48
     поддержку
    1.48
     поддержка
    1.46
     encouragement
    1.44
    Act Density 0.018%

    No Known Activations