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

    Neuronpedia

    INDEX
    Explanations

    mass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    атов
    -0.07
    dojo
    -0.07
    pression
    -0.07
    RIPT
    -0.06
    ző
    -0.06
    .analytics
    -0.06
    izard
    -0.06
    putation
    -0.06
     transformer
    -0.06
    L
    -0.06
    POSITIVE LOGITS
     mass
    0.08
     murderous
    0.07
    BBBB
    0.07
     whichever
    0.06
     branching
    0.06
    .accounts
    0.06
     Ecc
    0.06
     nervous
    0.06
    Advertisement
    0.06
     fourteen
    0.06
    Act Density 0.001%

    No Known Activations