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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.64
     ourselves
    -0.60
     safely
    -0.52
     oneself
    -0.49
    στά
    -0.49
     angles
    -0.47
     yourselves
    -0.47
     partea
    -0.46
     Outros
    -0.45
     himself
    -0.45
    POSITIVE LOGITS
    SequentialGroup
    0.57
    SharedCtor
    0.55
     المعيارى
    0.53
     MainAxisSize
    0.53
    iastical
    0.53
    BufferException
    0.52
     препратки
    0.50
    StructEnd
    0.49
    REWRITE
    0.49
    arwal
    0.48
    Act Density 0.003%

    No Known Activations