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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron is looking for HTML‐style table layout tokens and attributes (e.g. col, span, =, style).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     проб
    -0.07
     trance
    -0.06
    olves
    -0.06
    icking
    -0.06
    FullName
    -0.06
     unsustainable
    -0.06
    igth
    -0.06
     iterate
    -0.06
     compound
    -0.06
    wcs
    -0.06
    POSITIVE LOGITS
     Gent
    0.07
     '↵
    0.07
    ndon
    0.06
     `}↵
    0.06
     rooms
    0.06
     `↵
    0.06
    -da
    0.06
    ляються
    0.06
     Sunshine
    0.06
     [],↵
    0.06
    Act Density 0.001%

    No Known Activations