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

    Neuronpedia

    INDEX
    Explanations

    disappears

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibble
    -0.07
     ramp
    -0.06
     světě
    -0.06
    Serialized
    -0.06
     POP
    -0.06
     mex
    -0.06
    Rails
    -0.06
    aln
    -0.06
    '*
    -0.06
     relying
    -0.06
    POSITIVE LOGITS
     Shanghai
    0.07
     interests
    0.07
    Veter
    0.07
     Shore
    0.07
     taxes
    0.07
     img
    0.07
     torpedo
    0.07
    .Writer
    0.06
    Bid
    0.06
     Aboriginal
    0.06
    Act Density 0.000%

    No Known Activations