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

    Neuronpedia

    INDEX
    Explanations

    Stable Song

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     annualized
    0.25
     Stage
    0.24
     Translational
    0.24
     HEL
    0.23
     Intersection
    0.23
     Combo
    0.23
     Ultimate
    0.23
     Effective
    0.23
     Program
    0.22
     Broadband
    0.22
    POSITIVE LOGITS
    èrent
    0.21
    Then
    0.21
    Noeud
    0.20
    ción
    0.20
    iferous
    0.20
    ༸
    0.20
    पूर्वक
    0.19
    ืด
    0.19
     forbade
    0.19
    ාව
    0.19
    Act Density 0.000%

    No Known Activations