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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Buy
    -0.06
     they
    -0.06
     competing
    -0.06
    _sb
    -0.06
     woo
    -0.06
     DIY
    -0.06
     Lew
    -0.06
    里
    -0.06
     unsustainable
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     ic
    0.07
    VEST
    0.07
     vas
    0.07
     Vas
    0.07
     jedn
    0.07
     asbestos
    0.07
    AT
    0.07
     �
    0.07
    ンス
    0.07
    infos
    0.07
    Act Density 0.009%

    No Known Activations