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

    Neuronpedia

    INDEX
    Explanations

    requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rộng
    -0.09
     scammers
    -0.08
     litigation
    -0.08
    où
    -0.08
     Carnival
    -0.08
     scams
    -0.07
     lawsuits
    -0.07
     അനു�
    -0.07
    شق
    -0.07
     cheerful
    -0.07
    POSITIVE LOGITS
     imposed
    0.09
     preconce
    0.09
     anything
    0.09
     Enforcement
    0.09
     constraint
    0.08
    urity
    0.08
     enforcing
    0.08
     perfectly
    0.08
    anything
    0.08
     necesariamente
    0.08
    Act Density 0.026%

    No Known Activations