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

    Neuronpedia

    INDEX
    Explanations

    serialize

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recommend
    -0.08
     decisive
    -0.08
     Affordable
    -0.07
    ierge
    -0.07
     стар
    -0.07
     Poly
    -0.07
     ld
    -0.07
     issu
    -0.07
    汰
    -0.06
    现身
    -0.06
    POSITIVE LOGITS
    'Brien
    0.08
    『
    0.08
    メール
    0.07
    uo
    0.07
     PyQt
    0.07
     OS
    0.07
    ‧
    0.07
     disco
    0.07
    חום
    0.07
    TeV
    0.07
    Act Density 0.001%

    No Known Activations