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

    Neuronpedia

    INDEX
    Explanations

    famous spaceship

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आसान
    0.44
    रन
    0.43
    燔
    0.42
    astotal
    0.41
    易
    0.41
     Easier
    0.41
     DefaultTargets
    0.40
    Easy
    0.39
    枯
    0.39
    怛
    0.39
    POSITIVE LOGITS
     biceps
    0.63
     b
    0.51
     appet
    0.46
     appetite
    0.43
     bid
    0.41
     bich
    0.41
     bic
    0.39
     Appet
    0.39
    bid
    0.38
    clientID
    0.38
    Act Density 0.000%

    No Known Activations