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

    Neuronpedia

    INDEX
    Explanations

    annex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ship
    -0.07
    .Some
    -0.06
    .Uri
    -0.06
     capital
    -0.06
     lista
    -0.06
    Credit
    -0.06
    цит
    -0.06
     Budget
    -0.05
     режим
    -0.05
    Fault
    -0.05
    POSITIVE LOGITS
    elere
    0.07
    _HC
    0.07
    ΑΘ
    0.07
    言
    0.06
    πει
    0.06
     overwhel
    0.06
    介
    0.06
     jong
    0.06
    ylül
    0.06
    SOLE
    0.06
    Act Density 0.008%

    No Known Activations