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

    Neuronpedia

    INDEX
    Explanations

    something called

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     we
    0.35
     all
    0.34
     put
    0.34
     back
    0.33
     practitioners
    0.33
     you
    0.33
     count
    0.33
     crises
    0.33
     choose
    0.32
     crisis
    0.32
    POSITIVE LOGITS
    Pyrazole
    0.32
    Archae
    0.32
    室内
    0.31
    EtOH
    0.31
    0.31
     লইয়া
    0.31
    土産
    0.30
    GEBURTSORT
    0.30
    Rustic
    0.30
    adisu
    0.29
    Act Density 0.000%

    No Known Activations