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

    Neuronpedia

    INDEX
    Explanations

    Bi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shooting
    -0.07
    _REASON
    -0.07
    _dx
    -0.06
    infra
    -0.06
    物业服务
    -0.06
     Repository
    -0.06
    -information
    -0.06
     środ
    -0.06
     vak
    -0.06
    volent
    -0.06
    POSITIVE LOGITS
     honored
    0.08
    状元
    0.08
     Burr
    0.07
    链
    0.07
     [],↵
    0.07
    \',
    0.07
    AINS
    0.07
    şe
    0.07
    “,
    0.07
    盲目
    0.07
    Act Density 0.009%

    No Known Activations