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

    Neuronpedia

    INDEX
    Explanations

    mias

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Victim
    -0.83
    Victim
    -0.73
     victim
    -0.68
     Muscular
    -0.65
    最快更新
    -0.65
     Victims
    -0.63
     Paglinawan
    -0.63
    tonode
    -0.61
    fromnode
    -0.61
    
    -0.61
    POSITIVE LOGITS
    ly
    0.83
    ized
    0.81
    ised
    0.62
    mente
    0.59
    ization
    0.58
    ally
    0.56
    LY
    0.55
     setUp
    0.54
    ize
    0.54
    izing
    0.54
    Act Density 0.346%

    No Known Activations