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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bem
    -0.07
    CHEMY
    -0.06
    -0.06
    orical
    -0.06
     criticize
    -0.06
    NG
    -0.06
    HONE
    -0.06
    اءات
    -0.06
    だから
    -0.06
    asbourg
    -0.06
    POSITIVE LOGITS
     grands
    0.07
     mustard
    0.07
     Empire
    0.07
    StartElement
    0.07
    ]↵↵↵
    0.06
     intra
    0.06
    .Align
    0.06
     Earth
    0.06
     pNode
    0.06
     mailbox
    0.06
    Act Density 0.000%

    No Known Activations