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

    Neuronpedia

    INDEX
    Explanations

    business listings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Raw
    -0.06
    -actions
    -0.06
     bě
    -0.06
     Tep
    -0.06
     soy
    -0.06
     province
    -0.06
    Update
    -0.06
    носят
    -0.06
    aż
    -0.06
    める
    -0.06
    POSITIVE LOGITS
     damn
    0.07
    .Dir
    0.07
     Metadata
    0.07
    *******************************************************************************/↵
    0.07
    rah
    0.06
     cardio
    0.06
    SHOT
    0.06
     xxx
    0.06
    super
    0.06
     použití
    0.06
    Act Density 0.004%

    No Known Activations