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

    Neuronpedia

    INDEX
    Explanations

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hateful
    -0.06
    "=>
    -0.06
     Recon
    -0.06
    ,re
    -0.06
    ()?>
    -0.06
    .servlet
    -0.06
     thrive
    -0.06
    toBe
    -0.06
     odio
    -0.06
    &eacute
    -0.06
    POSITIVE LOGITS
     Oh
    0.07
    iless
    0.06
    Oh
    0.06
     Indian
    0.06
    lund
    0.06
    urgence
    0.06
     Arbit
    0.06
    祝
    0.06
    ิช
    0.06
    .buf
    0.06
    Act Density 0.025%

    No Known Activations