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

    Neuronpedia

    INDEX
    Explanations

    Math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Friendship
    -0.08
     Addiction
    -0.07
     telemetry
    -0.07
    /Auth
    -0.07
     desperation
    -0.07
    _dm
    -0.07
     Combo
    -0.07
     equivalence
    -0.07
     tịch
    -0.07
    _te
    -0.07
    POSITIVE LOGITS
     scattered
    0.06
    GOR
    0.06
    쥘
    0.06
    ]+
    0.06
     fres
    0.06
    	dd
    0.06
    /details
    0.06
    .returnValue
    0.06
     כבר
    0.06
    	fclose
    0.06
    Act Density 0.098%

    No Known Activations