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

    Neuronpedia

    INDEX
    Explanations

    Formal/critical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     French
    -0.80
    French
    -0.77
    \{\\
    -0.74
     Next
    -0.71
    Next
    -0.68
     french
    -0.61
    onAttach
    -0.60
    ConstraintMaker
    -0.59
     Roskov
    -0.57
    french
    -0.57
    POSITIVE LOGITS
    ness
    0.66
    ton
    0.57
    tings
    0.56
     становника
    0.56
    StatusBadRequest
    0.56
     papyrus
    0.54
     Liszt
    0.54
     Naira
    0.53
    ting
    0.52
    -|-
    0.52
    Act Density 0.186%

    No Known Activations