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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    든
    -0.07
     stole
    -0.07
    🧞
    -0.07
     Terminator
    -0.07
    煓
    -0.07
     הבא
    -0.07
     cole
    -0.07
    外套
    -0.07
    公网安备
    -0.06
    stück
    -0.06
    POSITIVE LOGITS
    ECH
    0.07
    sym
    0.07
    bay
    0.07
    -Agent
    0.07
     DISPLAY
    0.07
     ")↵↵
    0.07
    .IsMatch
    0.07
     MODE
    0.07
    )&
    0.07
    ATES
    0.06
    Act Density 0.015%

    No Known Activations