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

    Neuronpedia

    INDEX
    Explanations

    false

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imp
    -0.07
     Stitch
    -0.07
    ادم
    -0.07
    .sigmoid
    -0.07
    edeki
    -0.07
    .MixedReality
    -0.07
    .Persistent
    -0.07
     aggressively
    -0.06
    евич
    -0.06
    igan
    -0.06
    POSITIVE LOGITS
     false
    0.11
    False
    0.09
     False
    0.08
     falsely
    0.08
    false
    0.07
    še
    0.07
    absolute
    0.07
    WHO
    0.07
    	INT
    0.06
    pose
    0.06
    Act Density 0.004%

    No Known Activations