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

    Neuronpedia

    INDEX
    Explanations

    limerick

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meanwhile
    0.42
    suspended
    0.38
    hao
    0.38
    _{\{
    0.38
    onal
    0.38
    Meanwhile
    0.38
    caler
    0.37
    蝴
    0.37
     meanwhile
    0.36
     suspended
    0.36
    POSITIVE LOGITS
    icks
    0.83
    ick
    0.76
    ICK
    0.71
    ERICK
    0.66
    rick
    0.62
    ICKS
    0.62
    icki
    0.62
     rick
    0.60
    ricks
    0.59
    icksburg
    0.59
    Act Density 0.003%

    No Known Activations