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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    精品
    -0.07
    256
    -0.06
     viewpoint
    -0.06
    าห
    -0.06
    妃
    -0.06
    choice
    -0.06
    boost
    -0.06
    ту
    -0.06
    756
    -0.06
     stale
    -0.06
    POSITIVE LOGITS
     необ
    0.07
     ı
    0.07
    aternity
    0.06
    water
    0.06
    ↵↵↵↵↵↵↵↵
    0.06
     manufact
    0.06
    Pipe
    0.06
    	click
    0.06
    Vector
    0.06
    odia
    0.06
    Act Density 0.035%

    No Known Activations