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

    Neuronpedia

    INDEX
    Explanations

    product announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Harding
    -0.07
    booking
    -0.06
     Det
    -0.06
     Cancel
    -0.06
    Det
    -0.06
    unga
    -0.06
    	cursor
    -0.06
     distancing
    -0.06
     Devils
    -0.06
    け
    -0.06
    POSITIVE LOGITS
     scé
    0.07
     çift
    0.07
     ///↵
    0.07
    .bam
    0.06
    板
    0.06
    (JNIEnv
    0.06
    rodu
    0.06
    _INS
    0.06
     dorm
    0.06
    造成
    0.06
    Act Density 0.079%

    No Known Activations