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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Flags
    -0.07
    .store
    -0.07
    greg
    -0.06
    oley
    -0.06
    Testing
    -0.06
     oraz
    -0.06
    softmax
    -0.06
    UV
    -0.06
    tones
    -0.06
     kurul
    -0.06
    POSITIVE LOGITS
    ランド
    0.07
    -null
    0.07
    �s
    0.06
     фор
    0.06
    (movie
    0.06
    듯
    0.06
    ôt
    0.06
    vasive
    0.06
    ?“
    0.06
     Spells
    0.06
    Act Density 0.039%

    No Known Activations