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

    Neuronpedia

    INDEX
    Explanations

    calming and unwinding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கற்க
    0.41
     Fittings
    0.37
     कंड
    0.37
     stets
    0.37
    永久
    0.37
     enriqu
    0.36
     Enlarg
    0.36
     आजीवन
    0.36
     ayl
    0.36
     Enh
    0.35
    POSITIVE LOGITS
     reset
    1.08
     calming
    1.05
    reset
    0.97
     calmed
    0.97
    Reset
    0.96
     calm
    0.96
     Reset
    0.94
     успо
    0.93
     RESET
    0.91
    RESET
    0.89
    Act Density 0.083%

    No Known Activations