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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    deny
    -0.07
    .radius
    -0.06
    ��
    -0.06
     ORIGINAL
    -0.06
    ्तम
    -0.06
     Proposed
    -0.06
     ultimate
    -0.06
    lia
    -0.06
    lém
    -0.06
    ／/
    -0.06
    POSITIVE LOGITS
    -Tr
    0.07
    物
    0.07
    건
    0.06
    _detach
    0.06
    Device
    0.06
    ackage
    0.06
    таб
    0.06
     secrecy
    0.06
     उपय
    0.06
    Contains
    0.06
    Act Density 0.000%

    No Known Activations