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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tica
    -0.07
    充
    -0.06
    Starting
    -0.06
     kontro
    -0.06
    وست
    -0.06
    etooth
    -0.06
    ultimo
    -0.06
     �
    -0.06
     primero
    -0.06
    _effect
    -0.05
    POSITIVE LOGITS
    (dm
    0.07
    促
    0.07
    &M
    0.07
    
    0.07
     indicates
    0.07
     textSize
    0.06
     bytearray
    0.06
    Marsh
    0.06
     exclaimed
    0.06
     digs
    0.06
    Act Density 0.000%

    No Known Activations