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

    Neuronpedia

    INDEX
    Explanations

    people viewing content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ECC
    -0.07
    init
    -0.07
    ual
    -0.06
    ,+
    -0.06
     القر
    -0.06
     pedestal
    -0.06
    155
    -0.06
    第
    -0.06
    emergency
    -0.06
    parate
    -0.06
    POSITIVE LOGITS
     silently
    0.07
     baseUrl
    0.06
     bonus
    0.06
     INTER
    0.05
    규
    0.05
     INTERN
    0.05
     THESE
    0.05
     prayed
    0.05
    惊
    0.05
     đài
    0.05
    Act Density 0.023%

    No Known Activations