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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reclaim
    -0.07
    빌
    -0.07
     Initializes
    -0.06
     Θεσσα
    -0.06
     tedbir
    -0.06
    "):
    -0.06
     allo
    -0.06
     experimented
    -0.06
    .Rect
    -0.06
    (pid
    -0.06
    POSITIVE LOGITS
    -m
    0.11
    -s
    0.11
    -d
    0.11
    -c
    0.10
    -n
    0.10
    -h
    0.09
    -w
    0.09
    -l
    0.09
    -f
    0.09
    -t
    0.09
    Act Density 0.146%

    No Known Activations