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

    Neuronpedia

    INDEX
    Explanations

    mandatory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gun
    -0.08
    富
    -0.07
     fighter
    -0.07
     �
    -0.06
     scanner
    -0.06
    amp
    -0.06
     compass
    -0.06
    Cmd
    -0.06
     Viewer
    -0.06
     ten
    -0.06
    POSITIVE LOGITS
    媽
    0.08
    🌟
    0.08
     destabil
    0.07
    弄得
    0.07
    нст
    0.07
    )item
    0.07
     prer
    0.07
    .notNull
    0.07
    ereo
    0.07
     Cov
    0.07
    Act Density 0.016%

    No Known Activations