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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     userManager
    -0.07
     bigint
    -0.07
     frem
    -0.06
    .email
    -0.06
    descripcion
    -0.06
     responseType
    -0.06
     glu
    -0.06
     Donation
    -0.06
    Share
    -0.06
    hx
    -0.06
    POSITIVE LOGITS
    957
    0.07
    orners
    0.07
    	state
    0.06
     Assuming
    0.06
    ्ध
    0.06
    егда
    0.06
    (dr
    0.06
    のか
    0.06
    .WebControls
    0.06
     primera
    0.06
    Act Density 0.013%

    No Known Activations