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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     정신
    -0.08
    furt
    -0.07
     CHIP
    -0.07
     doğal
    -0.06
     quantum
    -0.06
    xhr
    -0.06
     payouts
    -0.06
     Miz
    -0.06
     |=
    -0.06
    _uuid
    -0.06
    POSITIVE LOGITS
    ави
    0.07
    
    0.06
     Pierce
    0.06
    -expression
    0.06
    补
    0.06
     marching
    0.06
     inclination
    0.06
    edral
    0.06
    ollar
    0.06
     Palestinians
    0.06
    Act Density 0.035%

    No Known Activations