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

    Neuronpedia

    INDEX
    Explanations

    Lean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     potom
    -0.07
     teplot
    -0.07
    �i
    -0.06
    ังก
    -0.06
    -0.06
    金属
    -0.06
    Acceleration
    -0.06
     빠
    -0.06
     onlar
    -0.06
    -0.06
    POSITIVE LOGITS
    _EMP
    0.08
     qualquer
    0.07
     Lean
    0.07
     lean
    0.07
     trying
    0.06
    leans
    0.06
     праці
    0.06
    _MAT
    0.06
     wrest
    0.06
    ’яз
    0.06
    Act Density 0.001%

    No Known Activations