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

    Neuronpedia

    INDEX
    Explanations

    parentheses and commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bit
    0.44
     shells
    0.44
    ID
    0.42
    model
    0.42
    launcher
    0.41
     portals
    0.39
    金額
    0.39
     hallmarks
    0.39
    Shell
    0.38
    du
    0.38
    POSITIVE LOGITS
     perse
    0.39
     permissible
    0.39
     Plac
    0.39
     boleh
    0.38
     आपला
    0.38
     보고
    0.37
     richi
    0.37
     perin
    0.36
    繇
    0.36
     Handbook
    0.36
    Act Density 0.001%

    No Known Activations