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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assessing
    -0.07
     Fra
    -0.07
    ｧ
    -0.07
     Horny
    -0.06
    /q
    -0.06
    ต
    -0.06
     drowning
    -0.06
    curity
    -0.06
     귀
    -0.06
     Experts
    -0.06
    POSITIVE LOGITS
     erb
    0.06
    .anchor
    0.06
    ,date
    0.06
     일반
    0.06
     mour
    0.06
     Broker
    0.06
     murm
    0.06
     strangers
    0.06
    ritt
    0.06
     setType
    0.06
    Act Density 0.081%

    No Known Activations