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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     llev
    -0.06
    亚
    -0.06
     autom
    -0.06
     Cake
    -0.06
    CRT
    -0.06
     금
    -0.06
     '';↵↵
    -0.06
     prayer
    -0.06
     рівні
    -0.06
    uridad
    -0.06
    POSITIVE LOGITS
    _estimator
    0.07
     zprav
    0.06
     setw
    0.06
     beneficiation
    0.06
    abr
    0.06
    ●●●●●●●●
    0.06
    程
    0.06
    щие
    0.06
    licts
    0.06
    instrument
    0.06
    Act Density 0.011%

    No Known Activations