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

    Neuronpedia

    INDEX
    Explanations

    into, throws, decided, apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kwietnia
    0.48
    ContextHeader
    0.47
     contextos
    0.45
     грудня
    0.44
     所以
    0.44
     Luckily
    0.42
     ကျွန်
    0.41
    ကျွန်
    0.41
    કિસ્
    0.40
    我又
    0.40
    POSITIVE LOGITS
    Drake
    0.41
    iš
    0.40
     drawable
    0.39
    Kraft
    0.38
    Tou
    0.38
    ená
    0.37
    如图
    0.37
    Son
    0.37
    Le
    0.36
    Char
    0.36
    Act Density 0.001%

    No Known Activations