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

    Neuronpedia

    INDEX
    Explanations

    health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BYTE
    -0.09
     catar
    -0.09
     Electronics
    -0.08
     prerecorded
    -0.08
     endocrine
    -0.08
     electronics
    -0.08
     serialized
    -0.08
     recorded
    -0.08
    ീര്
    -0.07
     Recorded
    -0.07
    POSITIVE LOGITS
    Pom
    0.09
     Pom
    0.08
    Apache
    0.08
    .so
    0.08
    $this
    0.08
     skut
    0.07
     shore
    0.07
    Lifestyle
    0.07
     dwelling
    0.07
    Though
    0.07
    Act Density 0.006%

    No Known Activations