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

    Neuronpedia

    INDEX
    Explanations

    suppress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brainstorm
    -0.07
     자연
    -0.07
     housing
    -0.07
     bere
    -0.06
     EAST
    -0.06
     Cathedral
    -0.06
     mocked
    -0.06
    -alpha
    -0.06
     bus
    -0.06
    bounded
    -0.06
    POSITIVE LOGITS
     千
    0.07
     çoğu
    0.07
    reported
    0.07
    ,exports
    0.06
    sorting
    0.06
    łe
    0.06
    猫
    0.06
    .hist
    0.06
     ))↵
    0.06
    zych
    0.06
    Act Density 0.003%

    No Known Activations