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

    Neuronpedia

    INDEX
    Explanations

    Tree traversal orders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (cnt
    -0.06
     worries
    -0.06
    (({
    -0.06
     Fi
    -0.06
    eil
    -0.06
     Griffith
    -0.06
    _o
    -0.06
     JComboBox
    -0.06
     Bernstein
    -0.06
     Ahmed
    -0.06
    POSITIVE LOGITS
    assessment
    0.07
    composer
    0.06
    Й
    0.06
     assemble
    0.06
    िसक
    0.06
     aud
    0.06
     simil
    0.06
     disorder
    0.06
     customs
    0.06
    ernals
    0.06
    Act Density 0.005%

    No Known Activations