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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PVC
    -0.06
    ’ta
    -0.06
     bỏ
    -0.06
     Monaco
    -0.06
    _cont
    -0.06
     phishing
    -0.06
     içi
    -0.06
    107
    -0.05
     věcí
    -0.05
     feet
    -0.05
    POSITIVE LOGITS
     Programming
    0.08
    _cache
    0.07
     lasted
    0.07
    ション
    0.07
    NDER
    0.07
    vably
    0.07
    uropean
    0.06
    τυ
    0.06
    	category
    0.06
     ss
    0.06
    Act Density 0.001%

    No Known Activations