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

    Neuronpedia

    INDEX
    Explanations

    Academic, code, copyright

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SEDS
    -0.55
    ListModule
    -0.54
    AMG
    -0.53
     osobow
    -0.52
    लय
    -0.52
    NgModule
    -0.51
    MCA
    -0.50
    las
    -0.49
    Abitanti
    -0.49
    forName
    -0.48
    POSITIVE LOGITS
     linear
    0.65
    KommentareTeilen
    0.61
     mergeFrom
    0.57
    Източници
    0.56
     Linear
    0.56
     المعيارى
    0.56
     ligiloj
    0.54
     liné
    0.52
    UpInside
    0.51
    linear
    0.50
    Act Density 0.000%

    No Known Activations