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

    Neuronpedia

    INDEX
    Explanations

    Tours

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sak
    -0.07
    (bucket
    -0.07
    (android
    -0.07
     Stats
    -0.07
     fiscal
    -0.07
    ですから
    -0.07
     });↵↵↵
    -0.07
     Geschichte
    -0.06
    となります
    -0.06
                            ↵
    -0.06
    POSITIVE LOGITS
    lijke
    0.07
    昂贵
    0.07
     charities
    0.07
     inventions
    0.07
     rare
    0.07
     Dagger
    0.07
    .MULT
    0.07
     dimin
    0.07
    𦭜
    0.07
     Purpose
    0.06
    Act Density 0.043%

    No Known Activations