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

    Neuronpedia

    INDEX
    Explanations

    previous steps or turns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transaction
    0.49
     customized
    0.47
     diffusion
    0.46
     danach
    0.43
     customizing
    0.42
     extrusion
    0.42
     процес
    0.42
    𝔦
    0.42
     beter
    0.42
     customizable
    0.42
    POSITIVE LOGITS
    VIOUS
    0.44
    UJ
    0.42
     Rother
    0.41
    Previous
    0.40
     précédentes
    0.40
    entures
    0.39
    accum
    0.38
     duly
    0.38
    Carry
    0.38
    previous
    0.37
    Act Density 0.001%

    No Known Activations