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

    Neuronpedia

    INDEX
    Explanations

    thinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OneToMany
    -0.08
    nowledge
    -0.07
     de
    -0.07
     גדולה
    -0.07
    优化
    -0.07
     property
    -0.07
    ɝ
    -0.07
    prisingly
    -0.06
     trust
    -0.06
    犯罪
    -0.06
    POSITIVE LOGITS
    _exchange
    0.08
    벡
    0.07
     Freak
    0.07
     בשם
    0.07
    냉
    0.06
     deb
    0.06
     ############
    0.06
    _pcm
    0.06
     '">
    0.06
     welt
    0.06
    Act Density 0.014%

    No Known Activations