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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‐'
    -0.08
     phủ
    -0.07
    39
    -0.07
     favicon
    -0.07
    _buy
    -0.07
    GLOSS
    -0.06
    벤
    -0.06
    endif
    -0.06
    -third
    -0.06
     gu
    -0.06
    POSITIVE LOGITS
     inorder
    0.07
    ูรณ
    0.07
     Per
    0.07
     Austin
    0.07
    Unauthorized
    0.07
     way
    0.06
    .try
    0.06
     PER
    0.06
    Per
    0.06
    _ARRAY
    0.06
    Act Density 0.016%

    No Known Activations