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

    Neuronpedia

    INDEX
    Explanations

    punctuation and conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ptrs
    -0.08
    Vectors
    -0.08
    .lex
    -0.07
    نسية
    -0.07
     mundo
    -0.07
    vice
    -0.07
     svých
    -0.07
     aspects
    -0.06
    _DIAG
    -0.06
    orean
    -0.06
    POSITIVE LOGITS
     folders
    0.06
     sil
    0.06
     gradual
    0.06
    _ADMIN
    0.06
     thermostat
    0.06
     isLoading
    0.06
     clothing
    0.06
     Mueller
    0.06
    �
    0.05
     Attached
    0.05
    Act Density 0.162%

    No Known Activations