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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Joshua
    -0.07
    �
    -0.07
     Oro
    -0.07
    เตร
    -0.07
    ařilo
    -0.07
    ByPrimaryKey
    -0.07
    备份
    -0.06
     teamwork
    -0.06
    infos
    -0.06
     spoken
    -0.06
    POSITIVE LOGITS
    ُل
    0.07
    Ra
    0.06
    реп
    0.06
    liament
    0.06
    복지
    0.06
    *);↵
    0.06
     secrecy
    0.06
     dicts
    0.06
    §Ã
    0.06
    mailbox
    0.06
    Act Density 0.433%

    No Known Activations