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

    Neuronpedia

    INDEX
    Explanations

    indicating duality or indirectness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endeu
    0.55
     എന്ത
    0.53
    ouvoir
    0.53
    ęb
    0.52
     Oekra
    0.52
    lande
    0.51
     Pltf
    0.51
     Dlatego
    0.50
    ostęp
    0.50
    쬐
    0.50
    POSITIVE LOGITS
    <0xE3>
    0.57
      
    0.52
    <0xE2>
    0.50
    \
    0.47
    ​
    0.46
    ス
    0.46
     Zen
    0.44
     vegetal
    0.44
    Hitting
    0.44
    ພ
    0.42
    Act Density 0.003%

    No Known Activations