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

    Neuronpedia

    INDEX
    Explanations

    .Diagnostics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [])
↵
    -0.07
    -girl
    -0.07
     PB
    -0.06
    network
    -0.06
    -ci
    -0.06
     ngắn
    -0.06
    CASCADE
    -0.06
    幼
    -0.06
    -reply
    -0.06
    欢
    -0.06
    POSITIVE LOGITS
    .Diagnostics
    0.08
     perform
    0.07
    ("---
    0.07
    _NEED
    0.07
    !=
    0.07
    dna
    0.07
    ètres
    0.07
     Estados
    0.06
     rein
    0.06
     Initializes
    0.06
    Act Density 0.000%

    No Known Activations