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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ount
    -0.06
     ว
    -0.06
     بده
    -0.06
    gen
    -0.06
     Sat
    -0.06
     Jahres
    -0.05
     druhý
    -0.05
    .Part
    -0.05
     jiný
    -0.05
    TECTION
    -0.05
    POSITIVE LOGITS
    >n
    0.07
     ______
    0.07
    _TMP
    0.07
    Envelope
    0.07
     Beast
    0.07
     brands
    0.06
     ################
    0.06
    tual
    0.06
    мор
    0.06
    >↵
    0.06
    Act Density 0.004%

    No Known Activations