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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tracks
    -0.07
     процед
    -0.06
    ancouver
    -0.06
     Software
    -0.06
    _DATE
    -0.06
     ctor
    -0.06
    OneToMany
    -0.06
    ็กซ
    -0.06
     Hardcover
    -0.06
     kes
    -0.06
    POSITIVE LOGITS
     fanc
    0.07
    {
↵
    0.07
     mainly
    0.06
     �
    0.06
    ensing
    0.06
     commencement
    0.06
    Ent
    0.06
    净
    0.06
    触
    0.06
     شکل
    0.06
    Act Density 0.007%

    No Known Activations