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

    Neuronpedia

    INDEX
    Explanations

    open square brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ボ
    -0.08
    741
    -0.07
    igel
    -0.07
    744
    -0.07
    bl
    -0.07
     Newsletter
    -0.07
    PostalCodesNL
    -0.07
    <h
    -0.06
     Onion
    -0.06
    нил
    -0.06
    POSITIVE LOGITS
     festivities
    0.07
    esseract
    0.06
    .CreateIndex
    0.06
    аты
    0.06
     Fade
    0.06
     Drama
    0.06
    "crypto
    0.06
     рассчит
    0.06
     commute
    0.06
     clim
    0.06
    Act Density 0.009%

    No Known Activations