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

    Neuronpedia

    INDEX
    Explanations

    things not working well

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .theme
    -0.07
     FORCE
    -0.06
    TURE
    -0.06
    _FINISH
    -0.06
    _dashboard
    -0.06
     Serial
    -0.06
     Paths
    -0.06
    .zip
    -0.06
     dictionaries
    -0.06
     Freed
    -0.06
    POSITIVE LOGITS
     Oops
    0.07
    inç
    0.06
     renk
    0.06
     нія
    0.06
    놓
    0.06
     surre
    0.06
    usable
    0.06
     ใช
    0.06
    营业
    0.06
     창
    0.06
    Act Density 0.081%

    No Known Activations