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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     voxel
    -0.07
    itud
    -0.07
    кого
    -0.07
     ssize
    -0.07
     expressive
    -0.07
    íš
    -0.07
     crystall
    -0.06
     Redux
    -0.06
    oggle
    -0.06
    ZD
    -0.06
    POSITIVE LOGITS
     Τ
    0.07
    }">↵
    0.06
    Perm
    0.06
     ";
↵
    0.06
    -equiv
    0.06
    써
    0.06
    _US
    0.06
    ไร
    0.06
     Buen
    0.06
     Voldemort
    0.05
    Act Density 0.012%

    No Known Activations