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

    Neuronpedia

    INDEX
    Explanations

    describing phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hazard
    0.42
    dancing
    0.39
     Prefer
    0.38
     Sally
    0.38
     !\
    0.38
     płyt
    0.38
     JES
    0.38
    izards
    0.36
    dance
    0.36
     Yellow
    0.36
    POSITIVE LOGITS
    rij
    0.37
    gan
    0.37
     pushed
    0.37
     endured
    0.37
    GAN
    0.36
     supervise
    0.36
    جين
    0.36
     अलै
    0.36
    衽
    0.35
     ज़ि
    0.35
    Act Density 0.000%

    No Known Activations