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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -dess
    -0.06
    ậu
    -0.06
    irmware
    -0.06
    EEE
    -0.06
     складу
    -0.06
    /support
    -0.06
     куда
    -0.06
     和
    -0.06
     puff
    -0.06
    尘
    -0.05
    POSITIVE LOGITS
    政府
    0.08
     praying
    0.07
     Hogan
    0.07
    VG
    0.07
    commerce
    0.07
    �
    0.07
     [(
    0.07
     sponsor
    0.06
    (opt
    0.06
    Em
    0.06
    Act Density 0.000%

    No Known Activations