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

    Neuronpedia

    INDEX
    Explanations

    Negative sentiment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -length
    -0.07
    Machine
    -0.07
    IFICATION
    -0.06
     declines
    -0.06
    (predicate
    -0.06
    ionales
    -0.06
    yx
    -0.06
     rigs
    -0.06
     podem
    -0.06
    .assign
    -0.06
    POSITIVE LOGITS
     Supporters
    0.06
     وا
    0.06
    느
    0.06
     робот
    0.06
     Princeton
    0.06
     правда
    0.06
    Emma
    0.06
    	NS
    0.06
     requestBody
    0.06
     м
    0.06
    Act Density 0.053%

    No Known Activations