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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weitere
    -0.08
     expecting
    -0.07
     unwrap
    -0.07
    /↵↵
    -0.06
     önemli
    -0.06
     Marco
    -0.06
    Der
    -0.06
     hal
    -0.06
     sadece
    -0.06
     cle
    -0.06
    POSITIVE LOGITS
     PCA
    0.08
     fittings
    0.07
     configs
    0.07
    _binary
    0.07
    fcntl
    0.06
    archives
    0.06
    (ev
    0.06
     t�
    0.06
    EMAIL
    0.06
     Documentation
    0.06
    Act Density 0.007%

    No Known Activations