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

    Neuronpedia

    INDEX
    Explanations

    communication and telling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Joy
    -0.08
    _err
    -0.07
     Pharmac
    -0.07
    偷
    -0.07
     exhibition
    -0.07
    afc
    -0.07
    _abs
    -0.06
    atoms
    -0.06
     inters
    -0.06
    (labels
    -0.06
    POSITIVE LOGITS
    leyici
    0.06
    шили
    0.06
     Strand
    0.06
    .getService
    0.06
    vely
    0.06
    _COMPILER
    0.06
    �
    0.06
     δεν
    0.06
     všech
    0.05
     öden
    0.05
    Act Density 0.069%

    No Known Activations