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

    Neuronpedia

    INDEX
    Explanations

    azo, Arcade, Aro

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    -2.38
     have
    -2.33
    ра
    -2.30
    ]
    -2.30
     knows
    -2.19
     {
    -2.17
    ;
    -2.11
    ’.
    -2.11
     In
    -2.06
     teh
    -2.06
    POSITIVE LOGITS
    翃
    3.05
    猻
    2.72
    呌
    2.55
    豋
    2.55
    ウォーター
    2.48
    釤
    2.42
    }$
    2.41
    孥
    2.34
    哥哥
    2.33
     PETITION
    2.27
    Act Density 0.002%

    No Known Activations