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

    Neuronpedia

    INDEX
    Explanations

    paper

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     PHY
    -0.06
     MagicMock
    -0.06
     SAC
    -0.05
     snug
    -0.05
    INCLUDING
    -0.05
     Stefan
    -0.05
    .question
    -0.05
    사가
    -0.05
     denomination
    -0.05
    POSITIVE LOGITS
     benefici
    0.07
     NCAA
    0.07
     initialize
    0.07
    ,state
    0.07
    _remain
    0.06
    Sibling
    0.06
    líč
    0.06
     JJ
    0.06
    =s
    0.06
     bullied
    0.06
    Act Density 0.015%

    No Known Activations