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

    Neuronpedia

    INDEX
    Explanations

    selected/drafted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    险
    -0.07
     fís
    -0.07
     Documentation
    -0.07
     Mont
    -0.06
    ิส
    -0.06
     आकर
    -0.06
     Demonstr
    -0.06
    �
    -0.06
    资
    -0.06
     đơn
    -0.06
    POSITIVE LOGITS
    IZE
    0.06
    anime
    0.06
    _but
    0.06
    icipant
    0.06
    estination
    0.06
    Bus
    0.06
    .slim
    0.05
    _Dec
    0.05
    	curl
    0.05
    /popper
    0.05
    Act Density 0.009%

    No Known Activations