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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    伊始
    -0.08
     );
↵
↵
    -0.07
    acus
    -0.07
    �
    -0.07
     [=[
    -0.06
    חום
    -0.06
    *****
↵
    -0.06
     ;;^
    -0.06
    }))↵↵
    -0.06
    LEASE
    -0.06
    POSITIVE LOGITS
    ليل
    0.07
    损失
    0.07
    Feel
    0.06
     Pok
    0.06
    _ip
    0.06
     hö
    0.06
    inger
    0.06
    퍄
    0.06
    ☛
    0.06
     focus
    0.06
    Act Density 0.001%

    No Known Activations