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

    Neuronpedia

    INDEX
    Explanations

    mathematical sequences and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bloc
    -0.07
    -monitor
    -0.07
     diz
    -0.07
    eder
    -0.07
    คณะกรรมการ
    -0.07
    -One
    -0.07
     Madness
    -0.07
    omination
    -0.06
    Thursday
    -0.06
    努力
    -0.06
    POSITIVE LOGITS
    쓻
    0.07
    爆款
    0.07
    )});↵
    0.06
     unlocks
    0.06
     pdu
    0.06
    شهاد
    0.06
    셀
    0.06
    淏
    0.06
    邂
    0.06
    trajectory
    0.06
    Act Density 0.007%

    No Known Activations