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

    Neuronpedia

    INDEX
    Explanations

    technical processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     caliente
    -0.07
    Healthy
    -0.07
    .Interop
    -0.06
     Cann
    -0.06
     verwendet
    -0.06
     aqui
    -0.06
    елів
    -0.06
     parfait
    -0.06
    ственно
    -0.06
    _FREQUENCY
    -0.06
    POSITIVE LOGITS
    .blue
    0.07
     xml
    0.07
     persuasion
    0.07
    .modify
    0.07
     getType
    0.06
    ----↵
    0.06
     django
    0.06
     Gui
    0.06
     antid
    0.06
     surgery
    0.06
    Act Density 0.000%

    No Known Activations