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

    Neuronpedia

    INDEX
    Explanations

    Moore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.07
    乡
    -0.07
    cepts
    -0.07
    eş
    -0.07
    	group
    -0.06
    Join
    -0.06
     Girl
    -0.06
     Apost
    -0.06
    691
    -0.06
     world
    -0.06
    POSITIVE LOGITS
     Shannon
    0.09
     Moore
    0.08
    MOOTH
    0.08
    -loaded
    0.08
    _likelihood
    0.07
     shallow
    0.07
     Reed
    0.07
     inconsistencies
    0.07
     fuller
    0.07
    .energy
    0.07
    Act Density 0.027%

    No Known Activations