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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Mar
    -0.08
     memiliki
    -0.07
    .jet
    -0.07
    /',
    -0.06
     Romero
    -0.06
     LoginActivity
    -0.06
     Infragistics
    -0.06
    _rent
    -0.06
    284
    -0.06
     Extra
    -0.06
    POSITIVE LOGITS
     압
    0.07
    RECT
    0.07
     пів
    0.07
    .fromFunction
    0.06
    %%↵
    0.06
    xdc
    0.06
     답
    0.06
    _TP
    0.06
    差
    0.06
     sus
    0.06
    Act Density 0.012%

    No Known Activations