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

    Neuronpedia

    INDEX
    Explanations

    markdown formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incapac
    -0.09
     यांच्या
    -0.08
    Eq
    -0.08
    ರಿಂದ
    -0.08
    chak
    -0.08
     theses
    -0.08
     occ
    -0.07
    TAG
    -0.07
     trots
    -0.07
     trot
    -0.07
    POSITIVE LOGITS
     remember
    0.08
     Minor
    0.08
     Augenmerk
    0.08
    istorical
    0.07
     noteworthy
    0.07
     meanwhile
    0.07
     lingu
    0.07
    אה
    0.07
    avelength
    0.07
     Remember
    0.07
    Act Density 0.044%

    No Known Activations