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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     placed
    -0.07
    "On
    -0.07
    Opt
    -0.07
    Index
    -0.07
     aspire
    -0.06
    enden
    -0.06
    وس
    -0.06
    .enter
    -0.06
    ounced
    -0.06
    ó
    -0.06
    POSITIVE LOGITS
     through
    0.12
     Through
    0.09
    ewood
    0.08
    through
    0.08
     walkthrough
    0.08
     túi
    0.08
    perf
    0.07
     thru
    0.07
    Through
    0.07
    -through
    0.07
    Act Density 0.028%

    No Known Activations