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

    Neuronpedia

    INDEX
    Explanations

    designs its own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ли
    0.39
    孤
    0.38
     reason
    0.36
    Decimal
    0.36
    罗
    0.36
     maddenin
    0.36
     seis
    0.35
    Calculator
    0.35
    DBG
    0.35
    ya
    0.34
    POSITIVE LOGITS
     SOFT
    0.39
    versorgung
    0.38
    诓
    0.38
    IZED
    0.38
     marketed
    0.37
     डिवीजन
    0.36
     devoted
    0.36
     करवाई
    0.36
    ivided
    0.36
    jä
    0.36
    Act Density 0.001%

    No Known Activations