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

    Neuronpedia

    INDEX
    Explanations

    ice and cold drinks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    onomy
    0.67
    ing
    0.60
    hemian
    0.56
    la
    0.54
    w
    0.54
    onian
    0.53
     in
    0.52
     elated
    0.52
    hemia
    0.51
    ath
    0.50
    POSITIVE LOGITS
    🍧
    0.89
     hielo
    0.87
     बर्फ
    0.73
    🧊
    0.73
    冰
    0.72
     śnie
    0.71
    ☃
    0.69
     アイス
    0.68
    ❄
    0.67
     охла
    0.67
    Act Density 0.011%

    No Known Activations