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

    Neuronpedia

    INDEX
    Explanations

    ">"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afr
    -0.07
    /problems
    -0.07
     план
    -0.07
    <\/
    -0.07
    ennis
    -0.07
    .Debugger
    -0.07
    -this
    -0.07
     daunting
    -0.07
    getManager
    -0.07
     Author
    -0.07
    POSITIVE LOGITS
     Expansion
    0.07
    ╏
    0.07
    ingly
    0.07
     forging
    0.07
    不过是
    0.07
    Deployment
    0.07
    hostname
    0.07
     timeless
    0.07
    霍
    0.06
    acies
    0.06
    Act Density 0.001%

    No Known Activations