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

    Neuronpedia

    INDEX
    Explanations

    code constructs or specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ARCHIVO
    0.49
     sentimiento
    0.41
    十九章
    0.41
     Röntgen
    0.38
     extrême
    0.38
    वायर
    0.38
    Después
    0.38
    🎹
    0.38
     lamented
    0.37
     sprinting
    0.37
    POSITIVE LOGITS
     Tag
    0.40
     Namely
    0.40
     Now
    0.39
     Link
    0.37
     Jez
    0.37
     جائے
    0.37
     diversify
    0.36
     expand
    0.36
     evoke
    0.36
     zh
    0.36
    Act Density 0.000%

    No Known Activations