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

    Neuronpedia

    INDEX
    Explanations

    speak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cab
    -0.07
     neighborhoods
    -0.07
     unterschied
    -0.06
     duplication
    -0.06
     iddi
    -0.06
     villagers
    -0.06
     radically
    -0.06
     досить
    -0.06
    δες
    -0.06
     traff
    -0.06
    POSITIVE LOGITS
    opoulos
    0.06
     CSA
    0.06
    ussen
    0.06
    papers
    0.06
     gambling
    0.06
    atoes
    0.06
     PhpStorm
    0.06
    atories
    0.06
     furious
    0.06
    _uri
    0.05
    Act Density 0.002%

    No Known Activations