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

    Neuronpedia

    INDEX
    Explanations

    producer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     run
    -0.07
     Ang
    -0.07
    营运
    -0.07
     hym
    -0.07
    toContain
    -0.07
     Mine
    -0.07
     край
    -0.07
    orbit
    -0.07
    Ang
    -0.07
    武器
    -0.06
    POSITIVE LOGITS
    rella
    0.07
    	IL
    0.07
    sep
    0.07
     callee
    0.07
    {j
    0.06
    ิด
    0.06
    ーム
    0.06
    为了更好
    0.06
    LY
    0.06
     Ultra
    0.06
    Act Density 0.006%

    No Known Activations