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

    Neuronpedia

    INDEX
    Explanations

    break

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     đích
    0.74
    Converters
    0.69
    ემის
    0.67
    ২১
    0.67
     finalidad
    0.66
    anyang
    0.66
    "{@
    0.65
    iprofloxacin
    0.64
     मकसद
    0.64
     становника
    0.63
    POSITIVE LOGITS
     пол
    0.78
     through
    0.76
     del
    0.71
     attraverso
    0.68
    through
    0.68
    wrench
    0.66
     apart
    0.64
     باور
    0.62
    PREFIX
    0.62
     delusion
    0.61
    Act Density 0.074%

    No Known Activations