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

    Neuronpedia

    INDEX
    Explanations

    000

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _HOUR
    -0.08
     training
    -0.07
    training
    -0.07
     refere
    -0.07
     Training
    -0.06
     вказ
    -0.06
    (*(
    -0.06
    ccess
    -0.06
    >false
    -0.06
    Japan
    -0.06
    POSITIVE LOGITS
     Arsenal
    0.07
    ész
    0.06
    	parser
    0.06
    ishi
    0.06
     hoodie
    0.06
     Hamm
    0.06
    uto
    0.06
     suis
    0.06
    ioso
    0.05
     Like
    0.05
    Act Density 0.005%

    No Known Activations