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

    Neuronpedia

    INDEX
    Explanations

    Providing information

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gar
    0.68
     utt
    0.66
     Vinc
    0.65
     GRE
    0.65
    gar
    0.64
    帰り
    0.63
     Gro
    0.63
     गुन
    0.63
     pus
    0.62
    ugar
    0.62
    POSITIVE LOGITS
    providing
    0.73
    Pointing
    0.72
    Questions
    0.70
    Providing
    0.69
     providing
    0.69
    ulative
    0.69
    mocha
    0.68
    ulating
    0.66
    complicated
    0.66
     Fragen
    0.66
    Act Density 0.066%

    No Known Activations