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

    Neuronpedia

    INDEX
    Explanations

    right hand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للغا
    -0.08
    促销
    -0.07
    .PrintWriter
    -0.07
    粗
    -0.07
    .base
    -0.07
    ateful
    -0.07
    ACEMENT
    -0.07
    ꕥ
    -0.07
     inf
    -0.06
    unny
    -0.06
    POSITIVE LOGITS
    arya
    0.07
    mse
    0.07
    衒
    0.07
     Persist
    0.06
    isci
    0.06
    仰
    0.06
    solver
    0.06
    LOOK
    0.06
    Paris
    0.06
    _allow
    0.06
    Act Density 0.011%

    No Known Activations