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

    Neuronpedia

    INDEX
    Explanations

    technical explanations and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ตาม
    0.52
     Pareto
    0.51
     ৃ
    0.50
     fin
    0.49
     IBM
    0.49
     notor
    0.48
     backsplash
    0.47
    "/>
    0.46
     Mitsubishi
    0.46
    ก็ตาม
    0.46
    POSITIVE LOGITS
    гле
    0.45
    rition
    0.43
    yers
    0.43
    '
    0.43
    ៥
    0.43
    gers
    0.42
    ູ່
    0.42
    reth
    0.42
    bl
    0.41
    ilege
    0.41
    Act Density 0.001%

    No Known Activations