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

    Neuronpedia

    INDEX
    Explanations

    right now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ামান
    0.77
     Layers
    0.75
    phy
    0.74
    䒑
    0.73
    彡
    0.72
     zirconia
    0.71
    Pulse
    0.71
     redundant
    0.71
    ffee
    0.71
    ോധ
    0.71
    POSITIVE LOGITS
    eous
    1.65
    leftharpoons
    1.35
    EOUS
    1.32
     wing
    1.30
     handed
    1.27
     ascension
    1.18
    wing
    1.15
    angles
    1.14
    ward
    1.13
    most
    1.12
    Act Density 0.074%

    No Known Activations