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

    Neuronpedia

    INDEX
    Explanations

    rate, time, speed, between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াসে
    0.82
    பன்
    0.79
     fortale
    0.78
     cang
    0.75
    饒
    0.75
    ⊰
    0.74
     maximize
    0.74
    ரும்
    0.72
     укреп
    0.72
    ತ್ವ
    0.72
    POSITIVE LOGITS
    between
    0.93
    Between
    0.88
     между
    0.84
     between
    0.84
     causada
    0.78
    -/-
    0.77
    之间的
    0.76
     tussen
    0.74
     variability
    0.74
    stderr
    0.74
    Act Density 0.000%

    No Known Activations