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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    photo
    -0.07
    WHERE
    -0.07
     Fauc
    -0.06
     halted
    -0.06
    .major
    -0.06
     pastor
    -0.06
    uggestion
    -0.06
     VIS
    -0.06
    mitters
    -0.06
    .mar
    -0.06
    POSITIVE LOGITS
    Shell
    0.07
    _search
    0.07
     respuesta
    0.06
     словами
    0.06
     Shell
    0.06
     тысяч
    0.06
    膜
    0.06
    =sum
    0.06
    (numbers
    0.06
    ;;;;
    0.06
    Act Density 0.011%

    No Known Activations