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

    Neuronpedia

    INDEX
    Explanations

    availability/permissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atal
    -0.26
    aload
    -0.25
    WithType
    -0.25
     cause
    -0.25
    åĪĨåĪ«
    -0.25
    _SPE
    -0.25
    æĬ¥éĶĢ
    -0.25
     disap
    -0.25
     refer
    -0.25
    istar
    -0.25
    POSITIVE LOGITS
    åºı
    0.28
     Growing
    0.27
    èĩªä¹ł
    0.27
     –↵↵
    0.25
    Verbose
    0.25
    living
    0.25
     doc
    0.25
    åŀł
    0.25
    æ²¹èĦĤ
    0.25
     sequences
    0.24
    Act Density 0.183%

    No Known Activations