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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UT
    -0.07
    logs
    -0.06
     GAM
    -0.06
     hours
    -0.06
    .Y
    -0.06
    waves
    -0.06
    <Array
    -0.06
    six
    -0.06
    Idx
    -0.06
     background
    -0.06
    POSITIVE LOGITS
     strconv
    0.07
    Chem
    0.06
     deutsche
    0.06
     nr
    0.06
     egreg
    0.06
     Batter
    0.06
    .Listener
    0.06
     celebr
    0.06
    CHANNEL
    0.06
     deneyim
    0.06
    Act Density 0.043%

    No Known Activations