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

    Neuronpedia

    INDEX
    Explanations

    booking instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :])
    0.46
     アー
    0.45
    .^
    0.44
     dismay
    0.41
     インテリア
    0.41
    /**/*
    0.41
    $
    0.41
    庾
    0.40
    '^
    0.40
    :</
    0.40
    POSITIVE LOGITS
     policías
    0.46
    វ
    0.46
     antiguas
    0.45
    இ
    0.45
     únicas
    0.44
    无
    0.43
     clás
    0.42
    ति
    0.42
    ح
    0.42
     difíciles
    0.41
    Act Density 0.005%

    No Known Activations