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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    幸好
    -0.07
    colon
    -0.07
    ировал
    -0.07
    �
    -0.07
     ⓘ
    -0.07
    すこと
    -0.07
    phys
    -0.07
    .transaction
    -0.07
    谢韵
    -0.06
    乖乖
    -0.06
    POSITIVE LOGITS
     ERA
    0.08
    _sim
    0.07
    ,out
    0.07
    VIP
    0.06
    �
    0.06
    _HOR
    0.06
     Tim
    0.06
    -leaning
    0.06
    (Server
    0.06
    街区
    0.06
    Act Density 0.000%

    No Known Activations