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

    Neuronpedia

    INDEX
    Explanations

    Oracle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opleft
    -0.07
    ******↵
    -0.06
    .null
    -0.06
    nearest
    -0.06
    	Buffer
    -0.06
    .Dark
    -0.06
    eş
    -0.06
     αποτε
    -0.06
    upgrade
    -0.06
     kaldı
    -0.06
    POSITIVE LOGITS
     OM
    0.07
    marine
    0.07
    clipse
    0.07
    scious
    0.07
    OM
    0.06
     internally
    0.06
     Perform
    0.06
    rogram
    0.06
     забезпечення
    0.06
    quests
    0.06
    Act Density 0.005%

    No Known Activations