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

    Neuronpedia

    INDEX
    Explanations

    programming / coding contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Emm
    0.41
    ম্ম
    0.38
    foot
    0.38
    uu
    0.37
    verfahren
    0.37
     mm
    0.37
    jø
    0.37
    Ton
    0.36
     unlawful
    0.36
     sav
    0.36
    POSITIVE LOGITS
     steve
    0.57
     Steve
    0.49
    Steve
    0.46
    руя
    0.42
    にお
    0.38
    其余
    0.38
    othelial
    0.38
     thunder
    0.37
    ellation
    0.37
     כא
    0.37
    Act Density 0.000%

    No Known Activations