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

    Neuronpedia

    INDEX
    Explanations

    synchronization and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indignation
    0.85
     altitudes
    0.83
     intentions
    0.78
     cures
    0.77
     implicated
    0.76
     Π
    0.76
     aches
    0.75
     seasoning
    0.74
     équ
    0.74
     seams
    0.72
    POSITIVE LOGITS
    ิก
    0.92
    чные
    0.82
    ä
    0.81
    ี
    0.81
    ность
    0.80
    iverr
    0.79
    на
    0.79
    𝐚
    0.79
    maschine
    0.77
    чную
    0.75
    Act Density 0.009%

    No Known Activations