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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AS
    -0.07
     controvers
    -0.07
    .For
    -0.06
     understands
    -0.06
    허
    -0.06
    Warnings
    -0.06
    VE
    -0.06
     Giang
    -0.06
     earrings
    -0.06
     Sevilla
    -0.06
    POSITIVE LOGITS
    alsex
    0.07
     حکم
    0.07
     amendments
    0.06
     Vive
    0.06
     Guardians
    0.06
    �
    0.06
     omit
    0.06
     armored
    0.06
    يع
    0.06
    ptides
    0.06
    Act Density 0.003%

    No Known Activations