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

    Neuronpedia

    INDEX
    Explanations

    We

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _continue
    -0.06
    แก
    -0.06
     loader
    -0.06
    odě
    -0.06
     bathrooms
    -0.06
    �
    -0.06
    学院
    -0.06
    Clo
    -0.06
    banana
    -0.06
    naz
    -0.06
    POSITIVE LOGITS
    *>*
    0.07
    ิมพ
    0.07
     π
    0.07
    Vk
    0.06
    ﻟ�
    0.06
     Working
    0.06
     twin
    0.06
     *(*
    0.06
    -ag
    0.06
     FILE
    0.06
    Act Density 0.012%

    No Known Activations