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

    Neuronpedia

    INDEX
    Explanations

    design patents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     can
    0.63
    rógeno
    0.61
     blockchain
    0.60
     freepik
    0.58
    ર
    0.58
    தாகவும்
    0.57
     resist
    0.57
    ítica
    0.56
     korišten
    0.55
     dépend
    0.55
    POSITIVE LOGITS
    -
    0.68
    Z
    0.63
    9
    0.62
    М
    0.60
    ت
    0.58
    <0x9B>
    0.57
    1
    0.57
    4
    0.57
    О
    0.56
    【
    0.56
    Act Density 0.001%

    No Known Activations