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

    Neuronpedia

    INDEX
    Explanations

    Negative situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rea
    -0.06
     gain
    -0.06
    loop
    -0.06
     Zac
    -0.06
    Profit
    -0.06
     Bra
    -0.06
     Glouce
    -0.06
    徐
    -0.05
     ارشد
    -0.05
     Lean
    -0.05
    POSITIVE LOGITS
    ])+
    0.07
    式会社
    0.07
    ęk
    0.07
    ')).
    0.07
    PTION
    0.06
     overridden
    0.06
     pwd
    0.06
    _IDX
    0.06
    ーデ
    0.06
     Sheridan
    0.06
    Act Density 0.044%

    No Known Activations