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

    Neuronpedia

    INDEX
    Explanations

    Years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ٪
    -0.07
     tolerate
    -0.07
     oriented
    -0.07
    _altern
    -0.06
    ่าท
    -0.06
     sixty
    -0.06
     invalidate
    -0.06
    cedure
    -0.06
     Norris
    -0.06
    alta
    -0.06
    POSITIVE LOGITS
     июня
    0.07
     будущ
    0.07
     bloggers
    0.06
    Logo
    0.06
     budding
    0.06
     могут
    0.06
    ิญญ
    0.06
    博
    0.06
     मन
    0.06
     midfield
    0.06
    Act Density 0.056%

    No Known Activations