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

    Neuronpedia

    INDEX
    Explanations

    large size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     massive
    -1.59
     enormous
    -1.53
    massive
    -1.50
     huge
    -1.47
    huge
    -1.44
     gigantic
    -1.41
    Massive
    -1.40
     HUGE
    -1.35
     énorme
    -1.32
    Huge
    -1.31
    POSITIVE LOGITS
    ness
    0.77
    ,
    0.59
    mente
    0.57
    ity
    0.57
    est
    0.56
    ization
    0.54
    ly
    0.52
    ory
    0.52
    mism
    0.52
    mer
    0.51
    Act Density 1.602%

    No Known Activations