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

    Neuronpedia

    INDEX
    Explanations

    say "-url"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Produces
    -0.08
    Signed
    -0.08
     Initializes
    -0.07
    Filled
    -0.07
     Nueva
    -0.07
     Called
    -0.07
     Vivian
    -0.07
     Illustrated
    -0.07
     Healthy
    -0.07
    Produced
    -0.07
    POSITIVE LOGITS
    /pl
    0.09
    "k
    0.09
    /drop
    0.08
    /k
    0.08
    (pl
    0.08
    "K
    0.08
    k
    0.08
    (k
    0.08
     /^\
    0.08
    .k
    0.08
    Act Density 0.001%

    No Known Activations