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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    the mention of military awards and decorations

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Sid
    -0.08
    stinence
    -0.07
    (Function
    -0.07
     Ezra
    -0.06
     Sid
    -0.06
     Contracts
    -0.06
    zv
    -0.06
     Van
    -0.06
     Tomáš
    -0.06
    FUN
    -0.06
    POSITIVE LOGITS
     RedirectToAction
    0.07
     clin
    0.06
     frost
    0.06
     dood
    0.06
     grounding
    0.06
    ор
    0.06
    。（
    0.06
    ++)↵
    0.06
    ερ
    0.06
     있으며
    0.06
    Act Density 0.005%

    No Known Activations