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

    Neuronpedia

    INDEX
    Explanations

    Ltd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’app
    -0.07
    /ar
    -0.07
    Kar
    -0.07
    verture
    -0.06
     geopol
    -0.06
    ังจาก
    -0.06
    imit
    -0.06
     eman
    -0.06
    、それ
    -0.06
     Kar
    -0.06
    POSITIVE LOGITS
    prd
    0.07
    CO
    0.07
     Ave
    0.07
     lbs
    0.07
     possível
    0.06
     Inc
    0.06
     Blvd
    0.06
     rates
    0.06
     pls
    0.06
     Salesforce
    0.06
    Act Density 0.024%

    No Known Activations