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

    Neuronpedia

    INDEX
    Explanations

    hypotheses and assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    showAlert
    0.44
     literalmente
    0.42
     Reveals
    0.41
    Obviously
    0.40
     obtiene
    0.39
    注意事項
    0.39
    幺
    0.39
     Preference
    0.38
     showAlert
    0.38
     Obviously
    0.37
    POSITIVE LOGITS
     assume
    1.14
    assume
    0.91
     presume
    0.85
     Assume
    0.83
     say
    0.80
    Assume
    0.79
     assumed
    0.77
     assum
    0.76
     assumes
    0.75
     conclude
    0.65
    Act Density 0.052%

    No Known Activations