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

    Neuronpedia

    INDEX
    Explanations

    data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     비롯
    -0.08
     ಅಂಗ
    -0.08
     ಆಸ
    -0.08
     സ്വന്ത
    -0.07
     Watts
    -0.07
     ಉದ್ಯ
    -0.07
     وغيرها
    -0.07
     ಎಂದ
    -0.07
     clic
    -0.07
    "><?=$
    -0.07
    POSITIVE LOGITS
     grouped
    0.08
     provenant
    0.08
    esite
    0.08
    -en
    0.08
    editable
    0.08
     dumping
    0.08
    Structured
    0.08
     kolon
    0.08
     enlisted
    0.08
     внутри
    0.08
    Act Density 0.062%

    No Known Activations