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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "And
    -0.07
     kindergarten
    -0.07
    -vis
    -0.07
    olin
    -0.07
     Katz
    -0.07
    “And
    -0.07
    .atomic
    -0.07
    ф
    -0.07
    ode
    -0.06
    탤
    -0.06
    POSITIVE LOGITS
     ]}↵
    0.07
     '/',↵
    0.07
     popup
    0.07
    괼
    0.06
     Sofa
    0.06
    有意思
    0.06
     \
↵
    0.06
     contests
    0.06
     рав
    0.06
     unc
    0.06
    Act Density 0.041%

    No Known Activations