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
    excel
    -0.07
    	internal
    -0.06
     '{}
    -0.06
    _username
    -0.06
     oasis
    -0.06
    _DELETED
    -0.06
    ::::::::
    -0.06
     TXT
    -0.06
     Zac
    -0.06
     exercitation
    -0.06
    POSITIVE LOGITS
    .clientY
    0.07
     위한
    0.07
    ্�
    0.07
     Het
    0.07
    assemble
    0.07
     önceki
    0.06
    (move
    0.06
     bude
    0.06
    .Alignment
    0.06
     Scenario
    0.06
    Act Density 0.006%

    No Known Activations