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

    Neuronpedia

    INDEX
    Explanations

    Comparing groups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DISCLAIMED
    -0.08
    .FloatTensor
    -0.08
     Halifax
    -0.07
     incredibly
    -0.06
    ة
    -0.06
    .sprite
    -0.06
    IMUM
    -0.06
     voor
    -0.06
     efficiency
    -0.06
    returns
    -0.06
    POSITIVE LOGITS
     paz
    0.07
    떳
    0.07
    ICENSE
    0.07
    𝗸
    0.07
     Gratuit
    0.06
     sway
    0.06
     blot
    0.06
     UC
    0.06
    𝖋
    0.06
    _under
    0.06
    Act Density 0.182%

    No Known Activations