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

    Neuronpedia

    INDEX
    Explanations

    errors and exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ect
    -0.06
    FINITY
    -0.06
     度
    -0.06
     celebrities
    -0.06
    ('%
    -0.06
     suicides
    -0.06
    BootApplication
    -0.06
    SJ
    -0.06
     grooming
    -0.06
     pall
    -0.06
    POSITIVE LOGITS
     JVM
    0.07
    getMock
    0.06
    ミュ
    0.06
     như
    0.06
     tweaked
    0.06
     wisely
    0.06
     Mister
    0.06
     XYZ
    0.06
    にして
    0.06
     Dmitry
    0.06
    Act Density 0.000%

    No Known Activations