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

    Neuronpedia

    INDEX
    Explanations

    costly consequences or potential outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    isman
    0.50
    స్
    0.47
    type
    0.45
    elses
    0.45
    點
    0.44
    ఈ
    0.44
    因为
    0.44
    assertions
    0.44
     около
    0.44
    ibilidad
    0.43
    POSITIVE LOGITS
     situate
    0.47
     ໜອງ
    0.46
    Gx
    0.44
     angolo
    0.44
     tourne
    0.44
     luna
    0.43
    biggl
    0.43
     marchio
    0.42
     Vez
    0.42
     productName
    0.42
    Act Density 0.001%

    No Known Activations