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

    Neuronpedia

    INDEX
    Explanations

    interventions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    show
    -0.07
    Race
    -0.07
     pictureBox
    -0.07
     wife
    -0.07
    .Site
    -0.07
     grades
    -0.07
     SHOW
    -0.07
    صور
    -0.07
    .NONE
    -0.07
     pear
    -0.07
    POSITIVE LOGITS
     interventions
    0.22
     intervention
    0.11
     Intervention
    0.11
    ervention
    0.08
    entions
    0.07
    erv
    0.07
    طبيق
    0.06
    ventional
    0.06
    052
    0.06
    0.06
    Act Density 0.005%

    No Known Activations