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

    Neuronpedia

    INDEX
    Explanations

    lets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    💚
    -0.08
    怯
    -0.07
    舣
    -0.07
    dıklar
    -0.07
    _UNSUPPORTED
    -0.07
    随时随地
    -0.07
    .Add
    -0.06
    愀
    -0.06
    ꒫
    -0.06
     propulsion
    -0.06
    POSITIVE LOGITS
    	head
    0.07
    耪
    0.07
    시
    0.07
     shot
    0.07
    .serial
    0.07
     boards
    0.07
     accrued
    0.07
     takeaway
    0.07
    新建
    0.06
    槍
    0.06
    Act Density 0.088%

    No Known Activations