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

    Neuronpedia

    INDEX
    Explanations

    mysql

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    坩
    -0.08
    	loop
    -0.08
    路过
    -0.07
    itmap
    -0.07
     wollen
    -0.07
     stars
    -0.07
    章
    -0.07
     executor
    -0.07
    其他人
    -0.07
    deer
    -0.07
    POSITIVE LOGITS
    _models
    0.07
    .BACK
    0.07
     mot
    0.07
    _ACL
    0.07
    vironment
    0.07
     Método
    0.07
    斩获
    0.07
     Effects
    0.06
    _management
    0.06
    umno
    0.06
    Act Density 0.003%

    No Known Activations