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

    Neuronpedia

    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ſch
    -0.63
     ſame
    -0.62
     ſen
    -0.62
     purpoſe
    -0.62
    close
    -0.61
     pleaſure
    -0.60
     Jefus
    -0.58
     raiſ
    -0.57
     becauſe
    -0.56
     ſou
    -0.56
    POSITIVE LOGITS
    ayaquil
    0.66
    MLLoader
    0.65
    s
    0.65
    ly
    0.64
    ernalia
    0.58
    sing
    0.54
    HasForeignKey
    0.54
    batore
    0.54
     getSystem
    0.54
    Przypisy
    0.53
    Act Density 0.157%

    No Known Activations