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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cub
    -0.08
     Beds
    -0.07
     Riding
    -0.07
    へと
    -0.07
    "%
    -0.06
     Mand
    -0.06
     Contemporary
    -0.06
     tale
    -0.06
     cowboy
    -0.06
     mastering
    -0.06
    POSITIVE LOGITS
    leader
    0.07
    trag
    0.07
     knocked
    0.07
    隊
    0.06
    عاد
    0.06
    apsible
    0.06
     SRC
    0.06
    िम
    0.06
    rovers
    0.06
    bling
    0.06
    Act Density 0.044%

    No Known Activations