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

    Neuronpedia

    INDEX
    Explanations

    power state, side connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    decre
    0.47
    Decre
    0.46
    telling
    0.43
     deliverance
    0.43
     using
    0.43
     gives
    0.42
     utilizing
    0.42
     disappro
    0.42
     tremendous
    0.40
     gör
    0.40
    POSITIVE LOGITS
     manchmal
    0.48
     eventuali
    0.44
     solit
    0.40
     IEquatable
    0.40
     roślin
    0.39
    ometimes
    0.38
     flanked
    0.38
    或其他
    0.38
    那些
    0.38
    和其他
    0.38
    Act Density 0.013%

    No Known Activations