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

    Neuronpedia

    INDEX
    Explanations

    game plays and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಅವನು
    0.39
     emulsions
    0.38
    zhou
    0.38
     monto
    0.37
     ligands
    0.37
     sigmoid
    0.37
     nou
    0.35
    ucius
    0.35
     specialising
    0.34
     caram
    0.34
    POSITIVE LOGITS
    pressure
    0.40
    Immediately
    0.39
     Immediately
    0.38
    Reset
    0.38
    reset
    0.38
    immediately
    0.37
    第一时间
    0.37
    Insert
    0.36
    oxygen
    0.36
     Spotlight
    0.36
    Act Density 0.006%

    No Known Activations