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

    Neuronpedia

    INDEX
    Explanations

    claimed/disclaimed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    square
    -0.06
     nó
    -0.06
    -secondary
    -0.06
    ]=="
    -0.06
    300
    -0.06
     العمل
    -0.06
    Laura
    -0.06
    rama
    -0.06
    laughter
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    conut
    0.07
    (balance
    0.06
    (net
    0.06
     Marino
    0.06
     unint
    0.06
    osi
    0.06
    _std
    0.06
    fec
    0.06
     Synd
    0.06
    sville
    0.06
    Act Density 0.001%

    No Known Activations