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

    Neuronpedia

    INDEX
    Explanations

    common phrases completing thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rs
    0.74
    zA
    0.69
    Seg
    0.69
    SIM
    0.69
    stru
    0.67
    Gru
    0.67
    EL
    0.66
    സ്സ
    0.66
    aru
    0.64
    gru
    0.63
    POSITIVE LOGITS
     Creator
    0.82
     Между
    0.80
     വ്യക്ത
    0.79
     creator
    0.76
     manifestly
    0.76
     Creators
    0.74
    TROLL
    0.74
    áneas
    0.73
     creó
    0.73
     científ
    0.72
    Act Density 0.000%

    No Known Activations