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

    Neuronpedia

    INDEX
    Explanations

    conn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aggregator
    -0.07
     surge
    -0.07
     उद
    -0.07
     thunk
    -0.07
     kita
    -0.07
    (track
    -0.07
     developer
    -0.07
     priori
    -0.07
    (area
    -0.07
     specified
    -0.07
    POSITIVE LOGITS
    connection
    0.10
    	connection
    0.09
    .connection
    0.09
    _connection
    0.09
     الاتصال
    0.09
     طوال
    0.09
     communic
    0.09
     conexion
    0.09
     Während
    0.08
    acciones
    0.08
    Act Density 0.005%

    No Known Activations