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

    Neuronpedia

    INDEX
    Explanations

    found

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagMode
    -1.06
    帖最后由
    -0.84
    انيف
    -0.84
    Referències
    -0.82
     GenerationType
    -0.81
     تضيفلها
    -0.81
    rungsseite
    -0.81
     NSCoder
    -0.79
     newOwner
    -0.79
     snippetHide
    -0.78
    POSITIVE LOGITS
     this
    0.85
     the
    0.80
     a
    0.79
     their
    0.77
     these
    0.74
     an
    0.71
     him
    0.65
     them
    0.65
     one
    0.63
     her
    0.58
    Act Density 0.166%

    No Known Activations