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

    Neuronpedia

    INDEX
    Explanations

    code and markup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vari
    -0.06
     баз
    -0.06
    _transition
    -0.06
    ition
    -0.06
     correctness
    -0.06
     BOX
    -0.06
    ipe
    -0.06
    (D
    -0.06
     Time
    -0.06
     staying
    -0.06
    POSITIVE LOGITS
    ществ
    0.07
     }}>↵
    0.06
     applauded
    0.06
     sincer
    0.06
     whites
    0.06
     bölge
    0.06
     urlencode
    0.06
    かに
    0.06
    apy
    0.06
    _CNTL
    0.06
    Act Density 0.000%

    No Known Activations