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

    Neuronpedia

    INDEX
    Explanations

    ny

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     décor
    -0.08
    tega
    -0.07
    团长
    -0.07
     Alvarez
    -0.07
    呋
    -0.07
     değiştir
    -0.07
    uppet
    -0.07
     axes
    -0.07
     diverted
    -0.07
    Subset
    -0.07
    POSITIVE LOGITS
    _allow
    0.08
    NY
    0.07
    odynamic
    0.07
    民俗
    0.07
    럼
    0.07
    宝贵
    0.07
    }});↵
    0.07
    ềm
    0.07
     Encyclopedia
    0.07
    니
    0.07
    Act Density 0.011%

    No Known Activations