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

    Neuronpedia

    INDEX
    Explanations

    191

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     como
    -0.06
     以
    -0.06
    	n
    -0.06
    fetch
    -0.06
    ктів
    -0.06
    фік
    -0.06
    --------------------------------------------------------------------------------
    -0.06
     swap
    -0.06
    _gap
    -0.06
     acest
    -0.06
    POSITIVE LOGITS
     flights
    0.06
    .WriteAll
    0.06
    idges
    0.06
    орту
    0.06
    Arrow
    0.06
    _SOURCE
    0.06
    CESS
    0.06
    assage
    0.06
    ICTURE
    0.06
    passes
    0.06
    Act Density 0.007%

    No Known Activations