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

    Neuronpedia

    INDEX
    Explanations

    diverse language fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Much
    0.70
    Only
    0.66
     Currently
    0.61
    эффици
    0.60
     nicotin
    0.60
    Experts
    0.60
     atualmente
    0.60
     விருப்ப
    0.60
    Currently
    0.59
     Much
    0.59
    POSITIVE LOGITS
    щими
    0.68
    가를
    0.66
    瞭
    0.64
     dere
    0.63
    పోయే
    0.62
    ί
    0.62
     by
    0.62
    鵬
    0.62
    iky
    0.62
     us
    0.62
    Act Density 0.036%

    No Known Activations