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

    Neuronpedia

    INDEX
    Explanations

    know if

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     espécie
    0.71
     mutil
    0.69
     duplo
    0.68
    λογία
    0.67
     viernes
    0.65
     alkoh
    0.65
     proposito
    0.65
     MG
    0.64
     உள்ப
    0.64
     cualquiera
    0.63
    POSITIVE LOGITS
     conducted
    0.61
    ucid
    0.60
     driveway
    0.58
    াজের
    0.57
    Conduct
    0.57
     Conducting
    0.56
    பை
    0.54
     who
    0.54
    сква
    0.54
    ↵
    0.53
    Act Density 0.027%

    No Known Activations