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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    INPUT
    -0.07
    estruct
    -0.06
    Statistic
    -0.06
     principalTable
    -0.06
    esen
    -0.06
    -Regular
    -0.06
    нему
    -0.06
    執
    -0.06
     alumnos
    -0.06
    сько
    -0.06
    POSITIVE LOGITS
    .getClient
    0.07
    ");↵
    0.07
    .backgroundColor
    0.07
     produk
    0.07
    iline
    0.07
     \↵
    0.07
    Model
    0.07
     Align
    0.06
    ]);↵
    0.06
    STORE
    0.06
    Act Density 0.006%

    No Known Activations