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

    Neuronpedia

    INDEX
    Explanations

    ma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fare
    -0.08
     Further
    -0.07
     forbidden
    -0.07
     Her
    -0.07
    _LOCAL
    -0.07
     Moy
    -0.06
     "↵↵
    -0.06
     متح
    -0.06
     questo
    -0.06
     breathing
    -0.06
    POSITIVE LOGITS
    RA
    0.07
    _DA
    0.07
    Ä
    0.07
    GA
    0.06
    also
    0.06
    ha
    0.06
     iP
    0.06
    (...
    0.06
    ีค
    0.06
     naj
    0.06
    Act Density 0.100%

    No Known Activations