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

    Neuronpedia

    INDEX
    Explanations

    casualties

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -real
    -0.07
     rush
    -0.06
    Global
    -0.06
    fiction
    -0.06
    rips
    -0.06
    .Environment
    -0.06
    ("/")
    -0.06
     nowhere
    -0.06
    Federal
    -0.06
    -Speed
    -0.06
    POSITIVE LOGITS
     зовніш
    0.07
    �
    0.07
     کمی
    0.07
    ivre
    0.06
    .SUCCESS
    0.06
    .astype
    0.06
     �
    0.06
     goalt
    0.06
     нарез
    0.06
     �
    0.06
    Act Density 0.028%

    No Known Activations