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

    Neuronpedia

    INDEX
    Explanations

    `attraction` `changes` `Impact`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.52
    Runtime
    0.52
    س
    0.51
    WARN
    0.49
    د
    0.49
    Selon
    0.47
    Kane
    0.47
    );
    0.46
    ا
    0.46
    ህ
    0.46
    POSITIVE LOGITS
    ayers
    0.54
     volleyball
    0.47
     breaching
    0.46
    讠
    0.46
     breaches
    0.46
     infections
    0.46
    光的
    0.45
     newspapers
    0.44
     fishermen
    0.44
    酢
    0.44
    Act Density 0.001%

    No Known Activations