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

    Neuronpedia

    INDEX
    Explanations

    drug safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    粝
    -0.07
     accounts
    -0.07
    📔
    -0.06
    ppelin
    -0.06
     me
    -0.06
    _at
    -0.06
    �
    -0.06
    下巴
    -0.06
     about
    -0.06
     perhaps
    -0.06
    POSITIVE LOGITS
     Chronic
    0.07
    KR
    0.07
     жидк
    0.07
     metam
    0.07
    .FR
    0.07
     ol
    0.07
    ,state
    0.07
    destruct
    0.07
     Entries
    0.07
     שהוא
    0.07
    Act Density 0.015%

    No Known Activations