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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्पन
    -0.07
    ISION
    -0.06
    眾
    -0.06
    adaptiveStyles
    -0.06
     khẩu
    -0.06
    од
    -0.06
    огра
    -0.06
     Persistence
    -0.06
    ocks
    -0.06
    чества
    -0.06
    POSITIVE LOGITS
     arter
    0.08
     Dost
    0.07
    'aut
    0.07
     jako
    0.07
     incorporates
    0.07
     Wise
    0.06
     juris
    0.06
     अस
    0.06
     comprise
    0.06
     +/-
    0.06
    Act Density 0.149%

    No Known Activations