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

    Neuronpedia

    INDEX
    Explanations

    old timestamp you the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     splitter
    0.52
     dysfunctional
    0.47
     bà
    0.47
     vocabulary
    0.46
     取り
    0.46
     logistic
    0.46
     necesariamente
    0.46
     rctx
    0.45
    クト
    0.45
     battle
    0.44
    POSITIVE LOGITS
    Broadway
    0.50
    Aub
    0.48
    Scr
    0.46
    DEM
    0.45
    THIS
    0.44
     Scratch
    0.44
    Harold
    0.44
    Huge
    0.44
    Ther
    0.44
    ASDW
    0.43
    Act Density 0.000%

    No Known Activations