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

    Neuronpedia

    INDEX
    Explanations

    credit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !=
    -0.07
    uci
    -0.07
     mile
    -0.06
     provincial
    -0.06
    でも
    -0.06
    ihn
    -0.06
     feet
    -0.06
    ALT
    -0.06
     defended
    -0.06
    alt
    -0.06
    POSITIVE LOGITS
    	Update
    0.08
     Archie
    0.07
    _follow
    0.07
     TimeSpan
    0.06
     toolkit
    0.06
    ncy
    0.06
     shorts
    0.06
     hesap
    0.06
     Öz
    0.06
     onUpdate
    0.06
    Act Density 0.008%

    No Known Activations