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

    Neuronpedia

    INDEX
    Explanations

    cannot fulfill your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mailbox
    0.66
     Chatter
    0.66
    ARGET
    0.64
    Brain
    0.64
    elang
    0.64
     चैट
    0.64
    rome
    0.63
    openapi
    0.63
     Sonya
    0.63
    heading
    0.63
    POSITIVE LOGITS
    displaystyle
    0.75
     requests
    0.74
     Requested
    0.71
     Requests
    0.71
    Request
    0.70
     requesting
    0.70
    Requests
    0.70
     request
    0.69
    ਪ
    0.67
     Request
    0.67
    Act Density 0.065%

    No Known Activations