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

    Neuronpedia

    INDEX
    Explanations

    say comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()>↵
    -0.07
    theme
    -0.07
     PV
    -0.06
     cling
    -0.06
     이유
    -0.06
     места
    -0.06
    between
    -0.06
     기
    -0.06
     PCs
    -0.06
    Photos
    -0.06
    POSITIVE LOGITS
    .Pop
    0.07
     عمل
    0.06
     manifested
    0.06
     Copa
    0.06
     melody
    0.06
     spouses
    0.06
    ··
    0.06
    objc
    0.06
     созд
    0.06
     POW
    0.06
    Act Density 0.117%

    No Known Activations