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

    Neuronpedia

    INDEX
    Explanations

    speed and around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gazprom
    0.54
     jednotliv
    0.53
     Zden
    0.52
     استعمال
    0.51
    علان
    0.51
    nst
    0.50
    phalodes
    0.49
     temporada
    0.48
     उद्योग
    0.48
     dispoz
    0.48
    POSITIVE LOGITS
    If
    0.43
    als
    0.43
    Fa
    0.42
     ruptured
    0.40
     synchronization
    0.40
     negotiating
    0.40
    L
    0.40
    of
    0.40
    ſt
    0.39
     wronged
    0.39
    Act Density 0.000%

    No Known Activations