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

    Neuronpedia

    INDEX
    Explanations

    Text formatting/descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intervenir
    -0.09
     intervient
    -0.09
     TED
    -0.08
     liberals
    -0.08
     estudiar
    -0.08
     Guinea
    -0.08
     unconstitutional
    -0.07
     dispositivos
    -0.07
     участия
    -0.07
     RAD
    -0.07
    POSITIVE LOGITS
     formatted
    0.11
     factual
    0.11
     newline
    0.11
    Whitespace
    0.10
    Formatted
    0.10
    Separated
    0.09
     concise
    0.09
     decorative
    0.09
    Footer
    0.09
     listing
    0.09
    Act Density 0.014%

    No Known Activations