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

    Neuronpedia

    INDEX
    Explanations

    Conversational/question texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MVP
    -0.06
     Jeg
    -0.06
    door
    -0.06
    PTR
    -0.06
    _HANDLE
    -0.06
    omu
    -0.06
    /task
    -0.06
    >\<^
    -0.06
    reu
    -0.06
    (routes
    -0.06
    POSITIVE LOGITS
     Laos
    0.08
    obraz
    0.07
     Addresses
    0.07
    doi
    0.06
    -parts
    0.06
    Abr
    0.06
    _sid
    0.06
     commitments
    0.06
    Physics
    0.06
    Ahead
    0.06
    Act Density 0.149%

    No Known Activations