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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erupt
    -0.08
     store
    -0.07
    -store
    -0.07
     Fluid
    -0.07
     trustworthy
    -0.07
    <>(
    -0.06
    fusion
    -0.06
     scores
    -0.06
    _parsed
    -0.06
    넷
    -0.06
    POSITIVE LOGITS
    tain
    0.08
    анов
    0.07
    那些
    0.07
     tote
    0.06
    Secret
    0.06
    sgiving
    0.06
     هل
    0.06
     suffering
    0.06
    _CONTROLLER
    0.06
     。
    0.06
    Act Density 0.018%

    No Known Activations