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

    Neuronpedia

    INDEX
    Explanations

    had

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CFR
    -0.07
    Java
    -0.07
     Carmen
    -0.06
     applies
    -0.06
    /Page
    -0.06
     Surgery
    -0.06
    								↵
    -0.06
     oslo
    -0.06
    OVID
    -0.06
    儀
    -0.06
    POSITIVE LOGITS
    ("[
    0.07
     Shannon
    0.07
    트
    0.06
    993
    0.06
    unning
    0.06
    etsy
    0.06
    sembles
    0.06
     minions
    0.06
     spawning
    0.06
    CREATE
    0.06
    Act Density 0.000%

    No Known Activations