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

    Neuronpedia

    INDEX
    Explanations

    marrow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fect
    -0.07
     és
    -0.06
    cea
    -0.06
    .fft
    -0.06
     joueur
    -0.06
     Gul
    -0.06
    variants
    -0.06
    adora
    -0.06
    (photo
    -0.06
    -aligned
    -0.06
    POSITIVE LOGITS
     marrow
    0.13
    場
    0.07
     exemption
    0.07
    _ak
    0.07
    ۲۷
    0.07
     goof
    0.06
    _ing
    0.06
     Sever
    0.06
    ,Th
    0.06
     Advocate
    0.06
    Act Density 0.001%

    No Known Activations